mlsanityData to 14 Oct 2026

7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting

arXiv 2503.07946 ↗First posted 11 Mar 2025cs.CV cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Real-time rendering of dynamic scenes with view-dependent effects remains a fundamental challenge in computer graphics. While recent advances in Gaussian Splatting have shown promising results separately handling dynamic scenes (4DGS) and view-dependent effects (6DGS), no existing method unifies these capabilities while maintaining real-time performance. We present 7D Gaussian Splatting (7DGS), a unified framework representing scene elements as seven-dimensional Gaussians spanning position (3D), time (1D), and viewing direction (3D). Our key contribution is an efficient conditional slicing mechanism that transforms 7D Gaussians into view- and time-conditioned 3D Gaussians, maintaining compatibility with existing 3D Gaussian Splatting pipelines while enabling joint optimization. Experiments demonstrate that 7DGS outperforms prior methods by up to 7.36 dB in PSNR while achieving real-time rendering (401 FPS) on challenging dynamic scenes with complex view-dependent effects. The project page is: https://gaozhongpai.github.io/7dgs/.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 35 of its 44 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

35 of 44 references.

References · 35

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  5. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  6. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  7. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  8. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  9. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  10. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  11. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  12. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
23 more
  1. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  2. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  3. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  4. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  5. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  6. 2023Robust Dynamic Radiance Fieldscited by 194
  7. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
  8. 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 111
  9. 20243D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesiscited by 109
  10. 2021Light Field Neural Renderingcited by 108
  11. 2024Fully Explicit Dynamic Gaussian Splattingcited by 76
  12. 2023Forward Flow for Novel View Synthesis of Dynamic Scenescited by 68
  13. 2024EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesiscited by 48
  14. 2023Flow supervision for Deformable NeRFcited by 42
  15. 2024Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Mediacited by 37
  16. 2025Radiant Foam: Real-Time Differentiable Ray Tracingcited by 34
  17. 2022Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Modelcited by 25
  18. 2024DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Renderingcited by 23
  19. 2024DaReNeRF: Direction-aware Representation for Dynamic Scenescited by 15
  20. 20246DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Renderingcited by 15
  21. 2022PREF: Predictability Regularized Neural Motion Fieldscited by 13
  22. 2024Unified Gaussian Primitives for Scene Representation and Renderingcited by 12
  23. 2024RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesiscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 13.

18 papers.

Sort:

By area:

  1. 2025Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videoscited by 8
  2. 2025Universal Beta Splattingcited by 4
  3. 20264C4D: 4 Camera 4D Gaussian Splattingcited by 4
  4. 2025HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatarscited by 3
  5. 2025Disentangled 4D Gaussian Splatting: Rendering High-Resolution Dynamic World at 343 FPScited by 1
  6. 2026SharpTimeGS: Sharp and Stable Dynamic Gaussian Splatting via Lifespan Modulationcited by 1
  7. 2026Decoupling Motion and Geometry in 4D Gaussian Splattingcited by 1
  8. 2026textit4DSurf: High-Fidelity Dynamic Scene Surface Reconstructioncited by 1
  9. 2026TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splattingcited by 1
  10. 2026On the Design of Mixture-of-Experts for Dynamic Gaussian Splattingcited by 1
  11. 2026XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splattingcited by 1
  12. 2025TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracingcited by 0
6 more
  1. 2026WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videoscited by 0
  2. 2026Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolationcited by 0
  3. 2026UniFusion: Sparse-View 4D Reconstruction via Unified Spatio-temporal Depth Alignmentcited by 0
  4. 2026Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed Camerascited by 0
  5. 2026FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Renderingcited by 0
  6. 2026Where Should the Gaussians Go? Reusable Label-Aware Allocation for Budget-Constrained Gaussian Splatting of Cinematic CTcited by 0