Research map / 3D vision / Gaussian splatting
7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting
Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Terrence Chen, Ziyan Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · 7DGS-PBR (avg) | PSNR: 31.77 -> 32.50 | Improved |
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · D-NeRF (avg) | PSNR: 33.26 -> 34.34 | Improved |
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · Technicolor (avg) | PSNR: 33.30 -> 33.58 | Improved |
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · 7DGS-PBR (avg) | FPS: 376.0 -> 174.7 | Hurt |
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · D-NeRF (avg) | FPS: 377.8 -> 194.2 | Hurt |
| add adaptive Gaussian refinement (AGR) (ablation) | 7DGS · Technicolor (avg) | FPS: 278.0 -> 79.2 | Hurt |
| replace 4DGS with 7DGS | 4DGS · 7DGS-PBR (avg) | PSNR: 27.79 -> 32.50 | Improved |
| replace 4DGS with 7DGS | 4DGS · D-NeRF (avg) | PSNR: 33.21 -> 34.34 | Improved |
| replace 4DGS with 7DGS | 4DGS · Technicolor (avg) | PSNR: 33.25 -> 33.58 | Improved |
| replace 4DGS with 7DGS | 4DGS · 7DGS-PBR (avg) | # points: 641,960 -> 98,440 | Improved |
| replace 4DGS with 7DGS | 4DGS · 7DGS-PBR heart1 | PSNR: 27.30 -> 35.48 | Improved |
| replace 4DGS with 7DGS | 4DGS · D-NeRF hook | PSNR: 32.93 -> 31.57 | Hurt |
Later papers that compared with this method
1 later accepted paper reports 7DGS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Universal Beta Splatting (ICLR 2026 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DaReNeRF — DaReNeRF: Direction-aware Representation for Dynamic Scenes (CVPR 2024) · better on 1 of 1 shared result
- HexPlane — HexPlane: A Fast Representation for Dynamic Scenes (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.94)
- 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025 · similarity 0.93)
- 1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering (NeurIPS 2025 · similarity 0.93)
- Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting (NeurIPS 2025 · similarity 0.93)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.93)
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering (CVPR 2025 · similarity 0.92)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
