MyPaper
暂存
CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting [paper] C3G: Learning Compact 3D Representations with 2K Gaussians [paper] [code] EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding [paper] [code] Learning Unified Representation of 3D Gaussian Splatting [paper] [code]
3DGS Segmentation
Feature Distillation-based Methods
LangSplat: 3D Language Gaussian Splatting [paper] [code] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields [paper] [code]
Enhancing Segmentation Accuracy.
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields [paper] LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding [paper] [code] Semantic Consistent Language Gaussian Splatting for Point-Level Open-vocabulary Querying [paper] [code] 3D Vision-Language Gaussian Splatting [paper] SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians [paper] [code] Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [paper] [code] econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians [paper] [code] 📑ReferSplat: Referring Segmentation in 3D Gaussian Splatting [paper] [code] COS3D: Collaborative Open-Vocabulary 3D Segmentation [paper] [code] GLS: Geometry-aware 3D Language Gaussian Splatting [paper] [code]
Efforts toward Efficiency and Compactness.
Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding [paper] [code] CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding [paper] [code] FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding [paper] [code] 👍️GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane [paper] [code] 👍️FastLGS: Speeding Up Language Embedded Gaussians with Feature Grid Mapping [paper] [code] FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agents [paper] Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression [paper] [code] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS [paper] [code]
2D Mask Lifting-based Methods
Consistency-Oriented Pre-Processing.
Gaussian Grouping: Segment and Edit Anything in 3D Scenes [paper] [code] Gaga: Group Any Gaussians via 3D-aware Memory Bank [paper] [code] Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field [paper] [code]
Consistency-Oriented Post-Processing.
OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning [paper] [code] CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting [paper] [code]
Consistency-Aware End-to-End Learning.
Segment Any 3D Gaussians [paper] [code] Segment Anything in 3D with Radiance Fields [paper] [code] Click-Gaussian: Interactive Segmentation to Any 3D Gaussians [paper] [code] Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting [paper] [code] OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding [paper] [code] VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding [paper] [code]
Joint Optimization of Multiple Cues.
COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting [paper] [code] PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding [paper] [code] InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception [paper] [code] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering [paper] [code]
Training-Free Mask Lifting.
SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition [paper] [code] ReferSplat: Referring Segmentation in 3D Gaussian Splatting [paper] [code] FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally [paper] [code] GaussianCut: Interactive Segmentation via Graph Cut for 3D Gaussian Splatting [paper] Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs [paper] [code] iSegMan: Interactive Segment-and-Manipulate 3D Gaussians [paper] [code] Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation [paper] LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes [paper] [code]
Feed-Forward-based Methods
Large Spatial Model: End-to-end Unposed Images to Semantic 3D [paper] [code] SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment [paper] [code] SLGaussian: Fast Language Gaussian Splatting in Sparse Views [paper] [code] Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration [paper] [code] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion [paper] [code] SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining [paper] [code]
A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding [paper] ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning [paper] [code] Zero-shot visual grounding in 3d gaussians via view retrieval [paper] [code] Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection [paper] 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection [paper] [code] MATT-GS: Masked Attention-based 3DGS for Robot Perception and Object Detection [paper]
3DGS Editing
Editing Based on Text Prompt
Localizing the Editing Object.
Gaussianeditor:Swift andcontrollable 3deditingwithgaussiansplatting [paper] [code] GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions [paper] GSEditPro: 3D Gaussian Splatting Editing with Attention‐based Progressive Localization [paper] Localized Gaussian Splatting Editing with Contextual Awareness [paper] Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling [paper] [code]
Efforts toward Multi-View Consistency.
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing [paper] [code] TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation [paper] Diffusion-Based Attention Warping for Consistent 3D Scene Editing [paper] [code] DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing [paper] [code] SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis [paper] [code] InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior [paper] Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing [paper] [code] Diffusion feature field for text-based 3d editing with gaussian splatting [paper]
Efforts toward Efficiency and Speed.
ProGDF: Progressive Gaussian Differential Field for Controllable and Flexible 3D Editing [paper] DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation [paper] [code] 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting [paper] [code] DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing [paper] [code] 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting [paper] [code]
Editing Based on Image Prompt
Parameter-Efficient Fine-Tuning.
TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts [paper] [code] GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting [paper] [code] PERSE: Personalized 3D Generative Avatars from A Single Portrait [paper] [code] Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing [paper] [code]
Improving Multi-View Consistency with Diffusion Models.
View-Consistent 3D Editing with Gaussian Splatting [paper] [code] TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing [paper] [code]
Multi-Stage Progressive Refinement.
Point'n Move: Interactive Scene Object Manipulation on Gaussian Splatting Radiance Fields [paper] [code] Neural Surface Priors for Editable Gaussian Splatting [paper] [code] GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting [paper] [code]
Style Transfer
Efforts toward Objective Function.
SGSST: Scaling Gaussian Splatting Style Transfer [paper] [code] ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting [paper] [code] WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians [paper] [code] Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles [paper] [code] CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting [paper] [code]
Efforts toward Integrating Diffusion Model.
InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splatting [paper] ArtNVG: Content-Style Separated Artistic Neighboring-View Gaussian Stylization [paper] Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization [paper] [code] FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting [paper] [code]
Efforts toward VGG Feature Optimization.
Gaussian Splatting in Style [paper] StyleSplat: 3D Object Style Transfer with Gaussian Splatting [paper] [code] StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting [paper] [code] Semanticsplatstylization: Semantic scene stylization based on 3d gaussian splatting and class based style transfer [paper]
Feed-Forward-based Model.
Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles [paper] [code] A3GS: Arbitrary Artistic Style into Arbitrary 3D Gaussian Splatting [paper] [code]
Other Editing Tasks
Object Removal.
Gaussian Grouping: Segment and Edit Anything in 3D Scenes [paper] [code] GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal [paper] [code] Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting [paper] [code]
Drag.
MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors [paper] [code] Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting [paper] [code]
Video Editing.
3DEgo: 3D Editing on the Go! [paper] [code] Portrait Video Editing Empowered by Multimodal Generative Priors [paper] [code]
Inpainting.
InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior [paper] [code] RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting [paper] Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency [paper]
3DGS Generation
3D GS
Drivable 3D Gaussian Avatars [paper] SparseGS: Real-Time 360° Sparse View Synthesis using Gaussian Splatting [paper] [code] Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting [paper] [code] GS-Pose: Cascaded Framework for Generalizable Segmentation-based 6D Object Pose Estimation [paper] [code] RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS [paper] RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion [paper] GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details [paper] EgoGaussian: Dynamic Scene Understanding from Egocentric Video with 3D Gaussian Splatting [paper] [code] HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors [paper] WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting [paper] [code] LoopSplat: Loop Closure by Registering 3D Gaussian Splats [paper] [code] DEGAS: Detailed Expressions on Full-Body Gaussian Avatars [paper] [code] ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [paper] [code] LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming [paper] DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction [paper] Direct and Explicit 3D Generation from a Single Image [paper] Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes [paper] AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for Indoor Room Reconstruction Using Smartphones [paper] [code] GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor [paper] E-3DGS: Event-Based Novel View Rendering of Large-Scale Scenes Using 3D Gaussian Splatting [paper] Open-Vocabulary Semantic Part Segmentation of 3D Human [paper] Segment Any 3D Gaussians [paper] [code] GFlow: Recovering 4D World from Monocular Video [paper] [code] DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians with Video Diffusion Priors [paper] [code] FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping [paper] TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers [paper] [code] DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input [paper] [code] Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding [paper] [code] PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis [paper] 3D2-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling [paper] [code] GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians [paper] [code] EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene [paper] [code] Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity [paper] GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance [paper] [code] KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image Sequences [paper] HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation [paper] DehazeGS: Seeing Through Fog with 3D Gaussian Splatting [paper] FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistency [paper] [code] BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene Generation [paper] [code] Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting [paper] Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images [paper] Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting [paper] [code] Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling [paper] ATLAS Navigator: Active Task-driven LAnguage-embedded Gaussian Splatting [paper] [code] Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian Splatting [paper] [code] CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image [paper] Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes [paper] Enhancing Close-up Novel View Synthesis via Pseudo-labeling [paper] Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles [paper] Street Gaussians without 3D Object Tracker [paper] SLGaussian: Fast Language Gaussian Splatting in Sparse Views [paper] [code] EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler [paper] [code] TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors [paper] [code] CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos [paper] [code] FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors [paper] FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting [paper] [code] Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections [paper] [code] Occlusion-Aware Temporally Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction [paper] Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction [paper] SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations [paper] GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting [paper] [code] 3DGabSplat: 3D Gabor Splatting for Frequency-adaptive Radiance Field Rendering [paper] Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation [paper] E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras [paper] TiP4GEN: Text to Immersive Panorama 4D Scene Generation [paper] SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion [paper] [code] SemanticGarment: Semantic-Controlled Generation and Editing of 3D Gaussian Garments [paper] PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion [paper] BSGS: Bi-stage 3D Gaussian Splatting for Camera Motion Deblurring [paper] [code] HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars [paper] Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video [paper] RUSplatting: Robust 3D Gaussian Splatting for Sparse-View Underwater Scene Reconstruction [paper] HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting [paper] Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams [paper] Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering [paper] MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing [paper] [code] DOF-GS:Adjustable Depth-of-Field 3D Gaussian Splatting for Post-Capture Refocusing, Defocus Rendering and Blur Removal [paper] [code] Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh [paper] [code] 3D-HGS: 3D Half-Gaussian Splatting [paper] [code] Improving Gaussian Splatting with Localized Points Management [paper] [code] Generative Gaussian Splatting for Unbounded 3D City Generation [paper] [code] WonderWorld: Interactive 3D Scene Generation from a Single Image [paper] [code] PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [paper] [code] Gaussian Eigen Models for Human Heads [paper] [code] FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering [paper] [code] Towards Realistic Example-based Modeling via 3D Gaussian Stitching [paper] [code] GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers [paper] [code] 3D-GSW: 3D Gaussian Splatting Watermark for Protecting Copyrights in Radiance Fields [paper] [code] Disco4D: Disentangled 4D Human Generation and Animation from a Single Image [paper] [code] RNG: Relightable Neural Gaussians [paper] [code] IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera [paper] [code] DepthSplat: Connecting Gaussian Splatting and Depth [paper] [code] SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes [paper] [code] GaussianSpa: An Optimizing-Sparsifying Simplification Framework for Compact and High-Quality 3D Gaussian Splatting [paper] [code] USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting [paper] [code] DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [paper] [code] FruitNinja: 3D Object Interior Texture Generation with Gaussian Splatting [paper] [code] VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving [paper] 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes [paper] [code] SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis [paper] [code] MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM [paper] [code] SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving [paper] [code] Geometry Field Splatting with Gaussian Surfels [paper] SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting [paper] [code] Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters [paper] [code] Textured Gaussians for Enhanced 3D Scene Appearance Modeling [paper] [code] InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception [paper] [code] TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting [paper] [code] GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting [paper] [code] Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives [paper] [code] Ref-GS: Directional Factorization for 2D Gaussian Splatting [paper] [code] SfM-Free 3D Gaussian Splatting via Hierarchical Training [paper] [code] Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes [paper] AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction [paper] [code] Volumetrically Consistent 3D Gaussian Rasterization [paper] [code] HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting [paper] [code] Multi-View Pose-Agnostic Change Localization with Zero Labels [paper] [code] Turbo3D: Ultra-fast Text-to-3D Generation [paper] [code] Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction [paper] [code] Splatter-360: Generalizable 360∘ Gaussian Splatting for Wide-baseline Panoramic Images [paper] [code] Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction [paper] [code] MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views [paper] [code] GASP: Gaussian Avatars with Synthetic Priors [paper] [code] GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [paper] [code] Feat2GS: Probing Visual Foundation Models with Gaussian Splatting [paper] [code] MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction [paper] [code] SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video [paper] [code] GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion [paper] [code] DCSEG: Decoupled 3D Open-Set Segmentation using Gaussian Splatting [paper] [code] PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting [paper] [code] 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting [paper] [code] Gaussian Splatting for Efficient Satellite Image Photogrammetry [paper] [code] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding [paper] [code] IDOL: Instant Photorealistic 3D Human Creation from a Single Image [paper] [code] Ref-GS: Modeling View-Dependent Appearance with Environment Gaussian [paper] [code] IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing [paper] [code] CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images [paper] [code] OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities [paper] [code] MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks [paper] [code] PERSE: Personalized 3D Generative Avatars from A Single Portrait [paper] [code] MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting [paper] [code] Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance [paper] [code] GauSTAR: Gaussian Surface Tracking and Reconstruction [paper] [code] Dense-SfM: Structure from Motion with Dense Consistent Matching [paper] UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping [paper] [code] Instruct-4DGS: Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation [paper] [code] AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting [paper] [code] 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency [paper] [code] Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration [paper] [code] DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting [paper] [code] Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior [paper] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models [paper] [code] Morpheus: Text-Driven 3D Gaussian Splat Shape and Color Stylization [paper] [code] NTR-Gaussian: Nighttime Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics [paper] [code] S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting [paper] [code] Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs [paper] [code] DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction [paper] [code] DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation [paper] SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting [paper] ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting [paper] HRAvatar: High-Quality and Relightable Gaussian Head Avatar [paper] [code] Mitigating Ambiguities in 3D Classification with Gaussian Splatting [paper] GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping [paper] [code] 4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models [paper] [code] SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs [paper] [code] RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars [paper] [code] Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting [paper] [code] RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images [paper] [code] BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting [paper] [code] RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos [paper] Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting [paper] TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting [paper] [code] PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding [paper] [code] DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds [paper] [code] 4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video [paper] Hardware-Rasterized Ray-Based Gaussian Splatting [paper] [code] NexusGS: Sparse View Synthesis with Epipolar Depth Priors in 3D Gaussian Splatting [paper] [code] HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting [paper] [code] From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting [paper] [code] COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting [paper] [code] GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting [paper] [code] PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model [paper] [code] Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields [paper] EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [paper] [code] Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields [paper] Photorealistic Simulation-Ready Garments from a Single Pose [paper] CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis [paper] RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting [paper] EVPGS: Enhanced View Prior Guidance for Splatting-based Extrapolated View Synthesis [paper] ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning [paper] DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting [paper] [code] Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views [paper] [code] LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors [paper] [code] Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration [paper] [code] Monocular and Generalizable Gaussian Talking Head Animation [paper] UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction [paper] DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting [paper] [code] Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment [paper] [code] Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting [paper] [code] Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model [paper] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments [paper] [code] PanoDreamer: Consistent Text to 360-Degree Scene Generation [paper] HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation [paper] [code] Wheat3DGS: In-field 3D Reconstruction, Instance Segmentation and Phenotyping of Wheat Heads with Gaussian Splatting [paper] [code] BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting [paper] DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering [paper] [code] ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos [paper] [code] SmallGS: Gaussian Splatting-based Camera Pose Estimation for Small-Baseline Videos [paper] [code] Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views [paper] SparSplat: Fast Multi-View Reconstruction with Generalizable 2D Gaussian Splatting [paper] SGCR: Spherical Gaussians for Efficient 3D Curve Reconstruction [paper] Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields [paper] SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation [paper] [code] Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation [paper] [code] Steepest Descent Density Control for Compact 3D Gaussian Splatting [paper] [code] Sparse Point Cloud Patches Rendering via Splitting 2D Gaussians [paper] [code] iSegMan: Interactive Segment-and-Manipulate 3D Gaussians [paper] [code] MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models [paper] [code] 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians [paper] [code] 3D Gaussian Splat Vulnerabilities [paper] FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting [paper] [code] FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction [paper] Gen4D: Synthesizing Humans and Scenes in the Wild [paper] VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction [paper] [code] FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity [paper] [code] UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting [paper] [code] GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction [paper] [code] SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting [paper] [code] DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting [paper] Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning [paper] [code] Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization [paper] DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis [paper] [code] ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting [paper] [code] 3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering [paper] See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization [paper] Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting [paper] GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting [paper] [code] 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt [paper] [code] Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats [paper] [code] MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes [paper] [code] LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes [paper] [code] Multimodal LLM Guided Exploration and Active Mapping using Fisher Information [paper] GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [paper] [code] Self-Ensembling Gaussian Splatting for Few-shot Novel View Synthesis [paper] [code] TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction [paper] [code] Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting [paper] GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting [paper] [code] Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction [paper] [code] EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting [paper] Sequential Gaussian Avatars with Hierarchical Motion Context [paper] [code] A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [paper] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models [paper] [code] EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding [paper] [code] FaceLift: Single Image to 3D Head with View Generation and GS-LRM [paper] [code] SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding [paper] [code] Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution [paper] [code] AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting [paper] GaussRender: Learning 3D Occupancy with Gaussian Rendering [paper] [code] Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction [paper] [code] GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow [paper] Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars [paper] MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light Conditions [paper] [code] CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images [paper] [code] SplatTalk: 3D VQA with Gaussian Splatting [paper] 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting [paper] DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction [paper] [code] Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation [paper] OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering [paper] [code] X^2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction [paper] [code] FlowR: Flowing from Sparse to Dense 3D Reconstructions [paper] SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets [paper] [code] DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting [paper] [code] GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR [paper] [code] HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction [paper] Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning [paper] Sparfels: Fast Reconstruction from Sparse Unposed Imagery [paper] GUAVA: Generalizable Upper Body 3D Gaussian Avatar [paper] [code] QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization [paper] SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations [paper] CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting [paper] SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images [paper] AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion [paper] RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [paper] [code] CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization [paper] [code] Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction [paper] [code] GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation [paper] RoboPearls: Editable Video Simulation for Robot Manipulation [paper] VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding [paper] RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors [paper] [code] From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting [paper] Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space [paper] [code] 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation [paper] [code] LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling [paper] Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps [paper] [code] VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis [paper] RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration [paper] [code] Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling [paper] [code] TRAN-D: 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update [paper] DCHM: Depth-Consistent Human Modeling for Multiview Detection [paper] [code] ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting [paper] [code] SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting [paper] [code] Gaussian Splatting with Discretized SDF for Relightable Assets [paper] [code] GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar [paper] DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering [paper] [code] HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars [paper] From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos [paper] GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections [paper] Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction [paper] NeRF Is a Valuable Assistant for 3D Gaussian Splatting [paper] MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction [paper] [code] Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis [paper] [code] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation [paper] [code] No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views [paper] [code] OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS [paper] [code] Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians [paper] [code] Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing [paper] [code] Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Framework [paper] MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction [paper] CF3: Compact and Fast 3D Feature Fields [paper] GAP: Gaussianize Any Point Clouds with Text Guidance [paper] [code] ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors [paper] Learning an Implicit Physics Model for Image-based Fluid Simulation [paper] GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments [paper] SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing [paper] [code] TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos [paper] WIPES: Wavelet-based Visual Primitives [paper] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos [paper] [code] GWM: Towards Scalable Gaussian World Models for Robotic Manipulation [paper] GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations [paper] Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images [paper] Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars [paper] [code] T2Bs: Text-to-Character Blendshapes via Video Generation [paper] EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device [paper] [code] PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [paper] [code] PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representation [paper] [code] SeHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing [paper] [code] StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions [paper] [code] Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency [paper] Hybrid Gaussian Splatting for Novel Urban View Synthesis [paper] Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering [paper] Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images [paper] Leveraging Learned Image Prior for 3D Gaussian Compression [paper] InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation [paper] HouseTour: A Virtual Real Estate A(I)gent [paper] [code] DIMO: Diverse 3D Motion Generation for Arbitrary Objects [paper] [code] Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud [paper] ErpGS: Equirectangular Image Rendering enhanced with 3D Gaussian Regularization [paper] Pose-free 3D Gaussian splatting via shape-ray estimation [paper] ICP-3DGS: SfM-free 3D Gaussian Splatting for Large-scale Unbounded Scenes [paper] [code] Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Monocular Videos [paper] [code] EG4D: Explicit Generation of 4D Object without Score Distillation [paper] [code] 3D StreetUnveiler with Semantic-Aware 2DGS [paper] [code] 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting [paper] [code] MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors [paper] Generalizable Human Gaussians from Single-View Image [paper] [code] InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting [paper] [code] Gaussian Splatting Lucas-Kanade [paper] GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting [paper] Atlas Gaussians Diffusion for 3D Generation with Infinite Number of Points [paper] [code] OmniRe: Omni Urban Scene Reconstruction [paper] [code] ThermalGaussian: Thermal 3D Gaussian Splatting [paper] Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection [paper] GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering [paper] [code] 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering [paper] RelitLRM: Generative Relightable Radiance for Large Reconstruction Models [paper] 3D Vision-Language Gaussian Splatting [paper] Fast Feedforward 3D Gaussian Splatting Compression [paper] [code] Poison-splat: Computation Cost Attack on 3D Gaussian Splatting [paper] [code] SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars [paper] [code] Sort-free Gaussian Splatting via Weighted Sum Rendering [paper] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [paper] [code] CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [paper] [code] SplatFormer: Point Transformer for Robust 3D Gaussian Splatting [paper] [code] Reflective Gaussian Splatting [paper] [code] STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes [paper] [code] Locality-aware Gaussian Compression for Fast and High-quality Rendering [paper] Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video [paper] [code] DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation [paper] [code] OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation [paper] [code] SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting [paper] Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors [paper] OMG: Opacity Matters in Material Modeling with Gaussian Splatting [paper] High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation [paper] [code] Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting [paper] UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting [paper] [code] Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting [paper] [code] CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression [paper] SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography [paper] Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene [paper] [code] 3D-Spatial MultiModal Memory [paper] [code] Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images [paper] [code] Divide-and-Conquer: Dual-Hierarchical Optimization for Semantic 4D Gaussian Spatting [paper] TC-GS: Tri-plane based compression for 3D Gaussian Splatting [paper] [code] ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splatting [paper] [code] Enhancing 3D Gaussian Splatting Compression via Spatial Condition-based Prediction [paper] ExScene: Free-View 3D Scene Reconstruction with Gaussian Splatting from a Single Image [paper] 3DBonsai: Structure-Aware Bonsai Modeling Using Conditioned 3D Gaussian Splatting [paper] ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting [paper] SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction [paper] PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [paper] [code] PEP-GS: Perceptually-Enhanced Precise Structured 3D Gaussians for View-Adaptive Rendering [paper] [code] HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder [paper] [code] Tackling View-Dependent Semantics in 3D Language Gaussian Splatting [paper] [code] VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians [paper] [code] Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting [paper] [code] ReferSplat: Referring Segmentation in 3D Gaussian Splatting [paper] [code] Gaussian-LIC: Photo-realistic LiDAR-Inertial-Camera SLAM with 3D Gaussian Splatting [paper] [code] AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction [paper] SAFER-Splat: A Control Barrier Function for Safe Navigation with Online Gaussian Splatting Maps [paper] [code] RenderWorld: World Model with Self-Supervised 3D Label [paper] Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splatting [paper] [code] MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting [paper] SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model [paper] [code] RL-GSBridge: 3D Gaussian Splatting Based Real2Sim2Real Method for Robotic Manipulation Learning [paper] [code] Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting [paper] [code] DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes [paper] WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting [paper] [code] Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and Mapping [paper] [code] GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM [paper] PUGS: Zero-shot Physical Understanding with Gaussian Splatting [paper] [code] RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes [paper] [code] OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding [paper] [code] Persistent Object Gaussian Splat (POGS) for Tracking Human and Robot Manipulation of Irregularly Shaped Objects [paper] [code] LiDAR-enhanced 3D Gaussian Splatting Mapping [paper] DLO-Splatting: Tracking Deformable Linear Objects Using 3D Gaussian Splatting [paper] Large-Scale Gaussian Splatting SLAM [paper] [code] Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM [paper] [code] FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field [paper] A Shared-Autonomy Construction Robotic System for Overhead Works [paper] SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM [paper] GRaD-Nav: Efficiently Learning Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics [paper] [code] GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction [paper] [code] Embracing Dynamics: Dynamics-aware 4D Gaussian Splatting SLAM [paper] FOCI: Trajectory Optimization on Gaussian Splats [paper] [code] 3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene [paper] ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects [paper] SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation [paper] [code] CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting [paper] [code] Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Features [paper] OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding [paper] [code] Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [paper] [code] Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction [paper] [code] Botany-Bot: Digital Twin Monitoring of Occluded and Underleaf Plant Structures with Gaussian Splats [paper] GRASPLAT: Enabling dexterous grasping through novel view synthesis [paper] STG-Avatar: Animatable Human Avatars via Spacetime Gaussian [paper] [code] Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenes [paper] iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion [paper] [code] EndoFlow-SLAM: Real-Time Endoscopic SLAM with Flow-Constrained Gaussian Splatting [paper] DIGS: Dynamic CBCT Reconstruction using Deformation-Informed 4D Gaussian Splatting and a Low-Rank Free-Form Deformation Model [paper] [code] Endo-4DGX: Robust Endoscopic Scene Reconstruction and Illumination Correction with Gaussian Splatting [paper] [code] SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting [paper] [code] Dyna3DGR: 4D Cardiac Motion Tracking with Dynamic 3D Gaussian Representation [paper] [code] Efficient 3D Scene Reconstruction and Simulation from Sparse Endoscopic Views [paper] BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation [paper] EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation [paper] Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting [paper] [code] Segment then Splat: A Unified Approach for 3D Open-Vocabulary Segmentation based on Gaussian Splatting [paper] [code] Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction [paper] CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting [paper] [code] LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering [paper] ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS [paper] [code] Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting [paper] BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading [paper] HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene [paper] Metropolis-Hastings Sampling for 3D Gaussian Reconstruction [paper] [code] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS [paper] [code] Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting [paper] Omni-Scan: Creating Visually-Accurate Digital Twin Object Models Using a Bimanual Robot with Handover and Gaussian Splat Merging [paper] Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting [paper] SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving [paper] HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis [paper] [code] Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos [paper] [code] MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics [paper] [code] VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment [paper] [code] DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion [paper] Fix False Transparency by Noise Guided Splatting [paper] [code] COS3D: Collaborative Open-Vocabulary 3D Segmentation [paper] [code] OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects [paper] VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting [paper] [code] PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors [paper] [code] AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians [paper] EA3D: Online Open-World 3D Object Extraction from Streaming Videos [paper] [code] HEIR: Learning Graph-Based Motion Hierarchies [paper] DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting [paper] [code] GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies [paper] IBGS: Image-Based Gaussian Splatting [paper] [code] TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming [paper] [code] Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion [paper] [code] DGH: Dynamic Gaussian Hair [paper] SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting [paper] [code] FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Rendering [paper] [code] LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation [paper] [code] SqueezeMe: Efficient Gaussian Avatars for VR [paper] SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting [paper] Deformable Beta Splatting [paper] [code] Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting [paper] [code] GigaSLAM: Large-Scale Monocular SLAM with Hierachical Gaussian Splats [paper] Generating 360° Video is What You Need For a 3D Scene [paper] In-2-4D: Inbetweening from Two Single-View Images to 4D Generation [paper] [code] TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians [paper] [code] Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting [paper] [code] TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling [paper] Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes [paper] [code] Monocular Online Reconstruction with Enhanced Detail Preservation [paper] EVA: Expressive Virtual Avatars from Multi-view Videos [paper] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views [paper] [code] WorldExplorer: Towards Generating Fully Navigable 3D Scenes [paper] On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images [paper] [code] Splat and Replace: 3D Reconstruction with Repetitive Elements [paper] SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction [paper] 3DGH: 3D Head Generation with Composable Hair and Face [paper] GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering [paper] [code] Gbake: Baking 3D Gaussian Splats into Reflection Probes [paper] ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions [paper] AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting [paper] [code] GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes [paper] PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems [paper] [code] LVT: Large-Scale Scene Reconstruction via Local View Transformers [paper] PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos [paper] Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures [paper] Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video [paper] [code] Clustered Error Correction with Grouped 4D Gaussian Splatting [paper] [code] Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction [paper] [code] DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting [paper] [code] GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis [paper] DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing [paper] [code] OmniGS: Omnidirectional Gaussian Splatting for Fast Radiance Field Reconstruction using Omnidirectional Images [paper] GaussianBeV: 3D Gaussian Representation meets Perception Models for BeV Segmentation [paper] Localized Gaussian Splatting Editing with Contextual Awareness [paper] LumiGauss: High-Fidelity Outdoor Relighting with 2D Gaussian Splatting [paper] [code] EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting [paper] [code] GStex: Per-Primitive Texturing of 2D Gaussian Splatting for Decoupled Appearance and Geometry Modeling [paper] [code] Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities [paper] [code] UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction [paper] ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting [paper] Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction [paper] [code] Planar Gaussian Splatting [paper] BeSplat -- Gaussian Splatting from a Single Blurry Image and Event Stream [paper] Lifting by Gaussians: A Simple, Fast and Flexible Method for 3D Instance Segmentation [paper] Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis [paper]
Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars [paper] GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects [paper] Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation [paper] [code] TexAvatars : Hybrid Texel-3D Representations for Stable Rigging of Photorealistic Gaussian Head Avatars [paper] [code] From Blurry to Believable: Enhancing Low-quality Talking Heads with 3D Generative Priors [paper] [code] FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting [paper] Vision-Only Gaussian Splatting for Collaborative Semantic Occupancy Prediction [paper] Arbitrary-Scale 3D Gaussian Super-Resolution [paper] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting [paper] [code] StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video [paper] [code] Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material Field [paper] [code] Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning [paper] [code] 4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation [paper] Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric [paper] [code] TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian Splatting [paper] [code] Multivariate Gaussian Representation Learning for Medical Action Evaluation [paper] PINGS-X: Physics-Informed Normalized Gaussian Splatting with Axes Alignment for Efficient Super-Resolution of 4D Flow MRI [paper] [code] SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images [paper] [code] GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving [paper] [code] Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitation [paper] SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction [paper] [code] Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting [paper] [code] GS-Checker: Tampering Localization for 3D Gaussian Splatting [paper] Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splatting [paper] [code] UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning [paper] [code] OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene Reconstruction [paper] [code] TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction [paper] GS-2M: Gaussian Splatting for Joint Mesh Reconstruction and Material Decomposition [paper] [code] RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience [paper] Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing [paper] GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars [paper] [code] Lightweight 3D Gaussian Splatting Compression via Video Codec [paper] [code] Voxel-GS: Quantized Scaffold Gaussian Splatting Compression with Run-Length Coding [paper] [code] GRTX: Efficient Ray Tracing for 3D Gaussian-Based Rendering [paper] VRGaussianAvatar: Integrating 3D Gaussian Avatars into VR [paper] [code] OFERA: Blendshape-driven 3D Gaussian Control for Occluded Facial Expression to Realistic Avatars in VR [paper] SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization [paper] [code] LeafFit: Plant Assets Creation from 3D Gaussian Splatting [paper] [code] HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars [paper] [code] MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second [paper] [code] iLRM: An Iterative Large 3D Reconstruction Model [paper] [code] Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images [paper] [code] REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting [paper] [code] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [paper] [code] FastGS: Training 3D Gaussian Splatting in 100 Seconds [paper] [code] STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction [paper] [code] EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images [paper] [code] GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation [paper] [code] ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking [paper] [code] Faster-GS: Analyzing and Improving Gaussian Splatting Optimization [paper] [code] B [paper] RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing [paper] [code] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction [paper] [code] RU4D-SLAM: Reweighting Uncertainty in Gaussian Splatting SLAM for 4D Scene Reconstruction [paper] [code] Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting [paper] [code] BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting [paper] AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction [paper] OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution [paper] EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding [paper] [code] Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists [paper] [code] VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM [paper] Gaussian Mesh Renderer for Lightweight Differentiable Rendering [paper] [code] Physics-Driven 3D Gaussian Rendering for Zero-Shot MRI Super-Resolution [paper] Gradient-Direction-Aware Density Control for 3D Gaussian Splatting [paper] [code] FastAvatar: Towards Unified Fast High-Fidelity 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers [paper] [code] MEGS2: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning [paper] [code] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation [paper] [code] WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving [paper] [code] Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting [paper] [code] Universal Beta Splatting [paper] [code] Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction [paper] [code] ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation [paper] [code] D2GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction [paper] [code] CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting [paper] Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer [paper] [code] G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior [paper] [code] Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction [paper] [code] VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator [paper] [code] FlashWorld: High-quality 3D Scene Generation within Seconds [paper] [code] MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting [paper] UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction [paper] [code] Sharp Monocular View Synthesis in Less Than a Second [paper] [code] A Step to Decouple Optimization in 3DGS [paper] SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors [paper] [code] UrbanGS: A Scalable and Efficient Architecture for Geometrically Accurate Large-Scene Reconstruction [paper] Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation [paper] [code] Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting [paper] Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement [paper] [code] DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics [paper] [code] RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI [paper] [code] Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation [paper] Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes [paper] GaussianCaR: Gaussian Splatting for Efficient Camera-Radar Fusion [paper] MipSLAM: Alias-Free Gaussian Splatting SLAM [paper] [code] Optimization-Free Style Transfer for 3D Gaussian Splats [paper] [code] Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes [paper] [code] SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering [paper] [code] CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting [paper]
暂存
Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy [code] Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation [code] OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation [code] Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation [code] Instance-Level Composed Image Retrieval [paper] [code] Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs [paper] [code] Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams
相关领域
From Pixels to Words – Towards Native Vision-Language Primitives at Scale [paper] [code] Exploring Cross-Modal Flows for Few-Shot Learning [paper] AnyUp: Universal Feature Upsampling [paper] CoT-PL: Visual Chain-of-Thought Reasoning Meets Pseudo-Labeling for Open-Vocabulary Object Detection [paper] Data or Language Supervision: What Makes CLIP Better than DINO? [paper] VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross Modal Mutual Information Maximization [paper] [code] Black Box Few-Shot Adaptation for Vision-Language models [paper] [code] Towards Calibrated Deep Clustering Network [paper] [code] Test-Time Adaptive Object Detection with Foundation Model [paper] [code] OVRD: OPEN-VOCABULARY RELATION DINO WITH TEXT-GUIDED SALIENT QUERY SELECTION [paper] [code] Towards Vision-Language Correspondence without Parallel Data [paper] [code] Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection [paper] [code] Fuse2Match: Training-Free Fusion of Flow,Diffusion, and Contrastive Models for Zero-Shot Semantic Matching [paper] [code] SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning [paper] OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts [paper] Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling [paper] [code]
多标签图像分类
Learning to Prompt for Vision-Language Models [paper] [code] PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification [paper] [code] Cdul: Clip-driven unsupervised learning for multi-label image classification [paper] [code] Language-driven Cross-modal Classifier for Zero-shot Multi-label Image Recognition [paper] [code] TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training [paper] [code] SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [paper] [code] Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification [paper] [code] Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport [paper] [code] Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning [paper] [code] MambaML: Exploring State Space Models for Multi-Label Image Classification [paper] Category-Specific Selective Feature Enhancement for Long-Tailed Multi-Label Image Classification [paper] [code] More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning [paper] [code] Language-Driven Multi-Label Zero-Shot Learning with Semantic Granularity [paper] [code]
Training-Free Open-Vocabulary Semantic Segmentation
Clip-diy: Clip dense inference yields open-vocabulary semantic segmentation for-free [paper] [code] Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation [paper] [code] Diffusion Models for Open-Vocabulary Segmentation [paper] [code] ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference [paper] [code] SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference [paper] [code] Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation [paper] [code] Proxyclip: Proxy attention improves clip for open-vocabulary segmentation [paper] [code] Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation [paper] [code] CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation [paper] [code] Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models [paper] [code] Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation [paper] In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation [paper] [code] LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation [paper] [code] ResCLIP: Residual Attention for Training-free Dense Vision-language Inference [paper] [code] Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation [paper] [code] Cheb-GR: Rethinking k-nearest neighbor search in Re-ranking for Person Re-identification [paper] [code] ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements [paper] [code] Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval [paper] [code] Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation [paper] [code] E-SAM: Training-Free Segment Every Entity Model [paper] ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation [paper] [code] CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation [paper] [code] CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting [paper] [code] Auto-Vocabulary Semantic Segmentation [paper] Training-Free Class Purification for Open-Vocabulary Semantic Segmentation [paper] [code] DIH-CLIP: Unleashing the Diversity of Multi-Head Self-Attention for Training-Free Open-Vocabulary Semantic Segmentation Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation [paper] [code] Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation [paper] [code] Test-Time Retrieval-Augmented Adaptation for Vision-Language Models [paper] [code] Images as Noisy Labels: Unleashing the Potential of the Diffusion Model for Open-Vocabulary Semantic Segmentation Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching [paper] Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [paper] [code] Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation [paper] [code] FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation [paper] [code] TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models [paper] [code] A Survey on Training-free Open-Vocabulary Semantic Segmentation [paper] No time to train! Training-Free Reference-Based Instance Segmentation [paper] [code] There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks [paper] [code] Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation [paper] Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation for Zero-shot Generalization [paper] [code] FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [paper] [code] TAG: Guidance-free Open-Vocabulary Semantic Segmentation [paper] [code] What Holds Back Open-Vocabulary Segmentation? [paper] Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers [paper] [code] SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP [paper] [code] Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP [paper] [code] IMPROVING VISUAL DISCRIMINABILITY OF CLIP FOR TRAINING-FREE OPEN-VOCABULARY SEMANTIC SEGMENTATION [paper] BEYOND OPEN-WORLD: COSRA, A TRAINING-FREE SELF-REFINING APPROACH TO OPEN-ENDED OBJECT DETECTION [paper] OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information [paper] Effective SAM Combination for Open-Vocabulary Semantic Segmentation [paper] Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective [paper] [code]
Training Open-Vocabulary Semantic Segmentation
GroupViT: Semantic Segmentation Emerges from Text Supervision [paper] [code] Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning [paper] Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs [paper] [code] Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only [paper] SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation [paper] [code] Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation [paper] [code] SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation [paper] [code] Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor [paper] USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation [paper] CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation [paper] [code] SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding [paper] CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation [paper] [code] CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction [paper] [code] Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels [paper] [code] Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation [paper] [[code]]DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment [paper] Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation [paper] [code] Your ViT is Secretly an Image Segmentation Model [paper] [code] Exploring Simple Open-Vocabulary Semantic Segmentation [paper] [code] Dual Semantic Guidance for Open Vocabulary Semantic Segmentation [paper] DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception [paper] [code] Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation [paper] [code] Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion [paper] [code] Text-guided Visual Prompt DINO for Generic Segmentation [paper] [code] Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision [paper] [code] High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation [paper] [code] Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [paper] [code] Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation [paper] [code] SegMASt3R: Geometry Grounded Segment Matching [paper] [code] Unified Open-World Segmentation with Multi-Modal Prompts [paper] [code] OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation [paper] [code]