Research map / 3D vision / NeRF and radiance fields
Forward Flow for Novel View Synthesis of Dynamic Scenes
Xiang Guo, Jiadai Sun, Yuchao Dai, Guanying Chen, Xiaoqing Ye, Xiao Tan, Errui Ding, Yumeng Zhang, Jingdong Wang
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 |
|---|---|---|---|
| use forward flow warping of canonical field instead of backward flow | dynamic NeRF · Lego Complete canonical interpolation | PSNR: 19.90 -> 25.63 (vs NDVG) | Improved |
| forward flow on D-NeRF dataset vs physical canonical baselines | dynamic NeRF · D-NeRF dataset | PSNR: 30.54 -> 32.68 (vs NDVG) | Improved |
| add inpaint network (ablation) | forward-flow NeRF · D-NeRF dataset | PSNR: 31.78 -> 32.68 | Improved |
| add upsampling in inpaint network (ablation) | forward-flow NeRF · D-NeRF dataset | PSNR: 32.03 -> 32.68 | Improved |
| add total variation losses (ablation) | forward-flow NeRF · D-NeRF dataset | PSNR / LPIPS: PSNR 33.09 -> 32.68; LPIPS 0.046 -> 0.037 | Mixed |
| add total variation losses (ablation) | forward-flow NeRF · HyperNeRF dataset | PSNR: 23.84 -> 24.23 | Improved |
| add photometric loss on upsampled grid (ablation) | forward-flow NeRF · D-NeRF 4 scenes | PSNR: 31.56 -> 33.75 | Improved |
| add flow loss (ablation) | forward-flow NeRF · D-NeRF 4 scenes | PSNR: 33.74 -> 33.75 | No clear effect |
| set canonical time to middle frame instead of first frame (ablation) | forward-flow NeRF · D-NeRF 4 scenes | PSNR: 33.75 -> 34.09 | Improved |
| voxel resolution limited to 70^3 versus 160^3 baselines | forward-flow NeRF · HyperNeRF dataset | PSNR: 24.2 vs 24.3 (TiNeuVox-B) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · better on 2 of 2 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
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.89)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.89)
- NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods (NeurIPS 2025 · similarity 0.89)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 2024 · similarity 0.89)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.89)
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.
