mlsanityData to 7 Oct 2026

Segment Any 4D Gaussians

arXiv 2407.04504 ↗First posted 5 Jul 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and understanding 3D scenes. Similarly, various 4D representations have demonstrated the ability to capture the dynamics of the 4D world. However, there is a dearth of research focusing on segmentation within 4D representations. In this paper, we propose Segment Any 4D Gaussians (SA4D), one of the first frameworks to segment anything in the 4D digital world based on 4D Gaussians. In SA4D, an efficient temporal identity feature field is introduced to handle Gaussian drifting, with the potential to learn precise identity features from noisy and sparse input. Additionally, a 4D segmentation refinement process is proposed to remove artifacts. Our SA4D achieves precise, high-quality segmentation within seconds in 4D Gaussians and shows the ability to remove, recolor, compose, and render high-quality anything masks. More demos are available at: https://jsxzs.github.io/sa4d/.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 68 of its 77 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

68 of 77 references.

References · 68

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2023Segment Anythingcited by 8,158
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  9. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  11. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  12. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
38 more
  1. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  3. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  4. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  5. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  6. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  7. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  8. 2022Language-driven Semantic Segmentationcited by 711
  9. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  10. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  11. 2023LERF: Language Embedded Radiance Fieldscited by 538
  12. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  13. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  14. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  15. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
  16. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  17. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  18. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  19. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  20. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  21. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  22. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  23. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  24. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  25. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  26. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  27. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  28. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 210
  29. 2023Tracking Anything with Decoupled Video Segmentationcited by 197
  30. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  31. 2023Robust Dynamic Radiance Fieldscited by 193
  32. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 185
  33. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 171
  34. 2023Segment Any 3D Gaussianscited by 158
  35. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  36. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  37. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  38. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 8.

19 papers.

Sort:

By area:

  1. 20254D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Modelscited by 35
  2. 20244D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitivescited by 15
  3. 2025Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fieldscited by 13
  4. 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localizationcited by 10
  5. 2024TRASE: Tracking-free 4D Segmentation and Editingcited by 8
  6. 2025Semantic Consistent Language Gaussian Splatting for Point-Level Open-vocabulary Queryingcited by 4
  7. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4
  8. 2025Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understandingcited by 2
  9. 2025Consistent Instance Field for Dynamic Scene Understandingcited by 2
  10. 2026Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstructioncited by 2
  11. 2025ROODI: Reconstructing Occluded Objects with Denoising Inpainterscited by 1
  12. 20264D Synchronized Fields: Motion-Language Gaussian Splatting for Temporal Scene Understandingcited by 1
7 more
  1. 2026PanopticQuery: Unified Query-Time Reasoning for 4D Scenescited by 1
  2. 2025Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Renderingcited by 0
  3. 2026TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentationcited by 0
  4. 2026Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understandingcited by 0
  5. 2026Accelerated Spatio-Temporal Gaussian Rendering via Kinematic and Semantic Priorscited by 0
  6. 2026Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocationcited by 0
  7. 2026S4VY: Segment Anything in Feed-Forward 4D Visual Geometrycited by 0