Research map / 3D vision / Depth and stereo
Monocular Dynamic View Synthesis: A Reality Check
Hang Gao, Ruilong Li, Shubham Tulsiani, Bryan Russell, Angjoo Kanazawa
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 |
|---|---|---|---|
| train on camera-teleporting (effective multi-view) sequences instead of non-teleporting monocular sequences (ablation) | NSFF, Nerfies, HyperNeRF, T-NeRF · Nerfies-HyperNeRF | mPSNR, mSSIM, mLPIPS, PCK-T | Mixed |
| add random background compositing, depth supervision and surface sparsity regularizer (+B+D+S) (ablation) | HyperNeRF · iPhone dataset | mPSNR/mLPIPS/PCK-T | Improved |
| use deformation-based models (Nerfies, HyperNeRF, NSFF) instead of plain T-NeRF | monocular DVS · iPhone dataset | mPSNR: 16.96 -> 16.81 | Hurt |
| evaluate on complex-motion iPhone data instead of Nerfies-HyperNeRF data | Nerfies · mPSNR | mPSNR: drops 4.4 dB | 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 0.89)
- Dynamic View Synthesis as an Inverse Problem (NeurIPS 2025 · similarity 0.89)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.87)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.87)
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (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.
