Research map / 3D vision / NeRF and radiance fields
MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos
Fengrui Tian, Shaoyi Du, Yueqi Duan
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 point feature F_dy (temporal + spatial) from video features (ablation) | MonoNeRF · Balloon2+Umbrella joint training | PSNR: 21.57 -> 24.44 | Improved |
| add temporal feature F_temp (ablation) | MonoNeRF · Balloon2+Umbrella joint training | PSNR: 23.80 -> 24.44 | Improved |
| add spatial feature F_sp (ablation) | MonoNeRF · Balloon2+Umbrella joint training | PSNR: 23.95 -> 24.44 | Improved |
| add random sampling of non-occluded frame for static features (ablation) | MonoNeRF · Training frames | PSNR: 17.30 -> 23.02 | Improved |
| add static field feature F_st (ablation) | MonoNeRF · Training frames | PSNR: 21.75 -> 23.02 | Improved |
| add depth-blending restriction L_db (ablation) | MonoNeRF · Unseen frames | PSNR: 20.69 -> 21.30 | Improved |
| add mask flow loss L_mf (ablation) | MonoNeRF · Unseen videos | PSNR: 21.67 -> 22.63 | Improved |
| use continuous Neural ODE solver instead of discretized trajectory (ablation) | MonoNeRF · Trajectory estimation | PSNR: 22.90 -> 23.75 (N=1 vs ODE) | Improved |
| replace positional encoding with video features (MonoNeRF) vs DynNeRF | DynNeRF · Dynamic Scene training frames | PSNR: 24.74 -> 25.62 | Improved |
| MonoNeRF vs DynNeRF on Playground scene | MonoNeRF · Playground training frames | PSNR: 23.65 -> 22.61 | Hurt |
Closest papers by meaning
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.89)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.88)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 2024 · similarity 0.88)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.87)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 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.
