Research map / 3D vision / Gaussian splatting
Fast View Synthesis of Casual Videos with Soup-of-Planes
Yao-Chih Lee, Zhoutong Zhang, Kevin Blackburn-Matzen, Simon Niklaus, Jianming Zhang, Jia-Bin Huang, Feng Liu
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 view-dependent appearance (spherical harmonics) to plane textures (ablation) | Soup-of-Planes static model · NVIDIA Dynamic Scene | LPIPS: 0.104 -> 0.084 | Improved |
| add view-dependent displacement to plane textures (ablation) | Soup-of-Planes static model · NVIDIA Dynamic Scene | LPIPS: 0.104 -> 0.087 | Improved |
| combine view-dependent appearance and displacement (ablation) | Soup-of-Planes static model · NVIDIA Dynamic Scene | PSNR: 23.14 -> 24.57 | Improved |
| add temporal neighbor blending for dynamic content (ablation) | Soup-of-Planes dynamic model · NVIDIA Dynamic Scene | PSNR: 24.48 -> 24.57 | No clear effect |
| disable scene flow regularization by default | Soup-of-Planes · training speed | training time | Improved |
| use explicit soup-of-planes plus per-frame point clouds instead of NeRF representations | casual video view synthesis · NVIDIA Dynamic Scene | training GPU hours: 320 (DynIBaR) -> 0.25 | Improved |
| use soup-of-planes instead of NeRF-based methods | casual video view synthesis · NVIDIA-long protocol | LPIPS: 0.027 (DynIBaR) vs 0.050 (Ours) | Hurt |
Closest papers by meaning
- Pseudo-Generalized Dynamic View Synthesis from a Video (ICLR 2024 · similarity 0.90)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.90)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.89)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.88)
- Dynamic View Synthesis as an Inverse Problem (NeurIPS 2025 · similarity 0.88)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.88)
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.
