Research map / 3D vision / NeRF and radiance fields
Dynamic View Synthesis From Dynamic Monocular Video
Chen Gao, Ayush Saraf, Johannes Kopf, Jia-Bin Huang
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 depth order loss (ablation) | Ours · Dynamic Scene Dataset (Playground) | PSNR: 22.99 -> 23.65 | Improved |
| add depth order loss (ablation) | Ours · Dynamic Scene Dataset (Playground) | LPIPS: 0.117 -> 0.093 | Improved |
| add motion matching loss (ablation) | Ours · Dynamic Scene Dataset (Playground) | PSNR: 22.61 -> 23.65 | Improved |
| add motion matching loss (ablation) | Ours · Dynamic Scene Dataset (Playground) | LPIPS: 0.137 -> 0.093 | Improved |
| add rigidity regularization of scene flow (ablation) | Ours · Dynamic Scene Dataset (Playground) | PSNR: 22.73 -> 23.65 | Improved |
| add rigidity regularization of scene flow (ablation) | Ours · Dynamic Scene Dataset (Playground) | SSIM: 0.8142 -> 0.8452 | Improved |
| add depth order loss (ablation) | Ours · Dynamic Scene Dataset (Playground) | SSIM: 0.8170 -> 0.8452 | Improved |
| add static NeRF and dynamic NeRF with scene flow regularization instead of NeRF + time | NeRF + time · Dynamic Scene Dataset (Playground) | PSNR (average): 17.30 -> 24.74 | Improved |
| separate static and dynamic NeRF versus plain NeRF | NeRF · Dynamic Scene Dataset (Playground) | PSNR (average): 21.62 -> 24.74 | Improved |
| Ours versus Yoon et al. depth warping | Yoon et al. · Dynamic Scene Dataset (Playground) | LPIPS (average): 0.153 -> 0.118 | Improved |
| Ours versus Li et al. on Skating | Li et al. · Dynamic Scene Dataset (Skating) | PSNR: 28.91 -> 28.90 | No clear effect |
Closest papers by meaning
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.91)
- Dynamic View Synthesis as an Inverse Problem (NeurIPS 2025 · similarity 0.91)
- Pseudo-Generalized Dynamic View Synthesis from a Video (ICLR 2024 · similarity 0.91)
- DyST: Towards Dynamic Neural Scene Representations on Real-World Videos (ICLR 2024 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · 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.
