Research map / 3D vision / Gaussian splatting
PackUV: Packed Gaussian UV Maps for 4D Volumetric Video
Aashish Rai, Angela Xing, Anushka Agarwal, Xiaoyan Cong, Zekun Li, Tao Lu, Aayush Prakash, Srinath Sridhar
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 direct UV-space optimization (UV init and pruning) instead of post-hoc UV projection (ablation) | PackUV-GS · PackUV-2B | PSNR: 23.81 -> 27.41 | Improved |
| add video keyframing (ablation) | PackUV-GS · PackUV-2B | PSNR: 20.95 -> 27.41 | Improved |
| add flow-guided Gaussian labeling (ablation) | PackUV-GS · PackUV-2B | PSNR: 25.42 -> 27.41 | Improved |
| pack layers into a single atlas (ablation) | PackUV-GS · PackUV-2B | PSNR: 27.43 -> 27.41 | No clear effect |
| add low-precision optimization (8-bit) (ablation) | PackUV-GS · PackUV-2B | PSNR: 27.52 -> 27.41 | No clear effect |
| add lossless video codec (FFV1) (ablation) | PackUV-GS · PackUV-2B | PSNR: 27.41 -> 27.41 | No clear effect |
| FFV1 lossless compression with 8-bit LPO (ablation) | PackUV · compression evaluation | PSNR: 0.11 dB | No clear effect |
| PackUV-GS vs strongest baseline 3DGStream | PackUV-GS · PackUV-2B | PSNR: 23.17 -> 27.41 | Improved |
| PackUV-GS vs GIFStream storage | PackUV-GS · 30 frames | storage (MB): 16 -> 10 | Improved |
| neural compression of atlas | PackUV · neural compression | PSNR drop: 1.5 dB to 4.5 dB | Hurt |
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.
- 3DGStream — 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024) · better on 5 of 5 shared results
- Grid4D — Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting (NeurIPS 2024) · better on 3 of 3 shared results
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
- Instant4D: 4D Gaussian Splatting in Minutes (NeurIPS 2025 · similarity 0.89)
- Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors (NeurIPS 2026 · similarity 0.88)
- 4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming (NeurIPS 2025 · similarity 0.88)
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.87)
- L4GM: Large 4D Gaussian Reconstruction Model (NeurIPS 2024 · similarity 0.87)
- 4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video (CVPR 2025 · similarity 0.87)
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.
