Research map / 3D vision / NeRF and radiance fields
Neural Radiance Flow for 4D View Synthesis and Video Processing
Yilun Du, Yinan Zhang, Hong-Xing Yu, Joshua B. Tenenbaum, Jiajun Wu
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 temporal consistency losses (ablation) | NeRFlow · Pouring, Dual Views | PSNR: 31.80 -> 35.29 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Pouring, Stereo Views | PSNR: 27.98 -> 28.29 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Pouring, Sparse Timestamps | PSNR: 33.75 -> 35.87 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Pouring, Full View | PSNR: 36.30 -> 36.57 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Gibson, Dual Views | PSNR: 22.26 -> 24.84 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Gibson, Stereo Views | LPIPS: 0.2806 -> 0.2496 | Improved |
| add temporal consistency losses (ablation) | NeRFlow · Gibson, Full View | MSE: 0.0028 -> 0.0029 | No clear effect |
| add temporal consistency losses (depth) (ablation) | NeRFlow · Pouring depth estimation, Stereo Views | depth MSE: 0.4433 -> 0.2701 | Improved |
| add temporal consistency losses (depth) (ablation) | NeRFlow · Pouring depth estimation, Full View | depth MSE: 0.3747 -> 0.3692 | No clear effect |
| NeRFlow versus NonRigid NeRF baseline | NeRFlow · Pouring, Dual Views | PSNR: 28.12 -> 35.29 | Improved |
| NeRFlow versus X-Fields baseline | NeRFlow · Gibson, Stereo Views | PSNR: 17.75 -> 23.65 | Improved |
| remove motion consistency (w/o Motion Consist.) (ablation) | NeRFlow · Pouring Stereo Views | qualitative | Hurt |
Closest papers by meaning
- Neural Radiance Fields From Sparse RGB-D Images for High-Quality View Synthesis (TPAMI 2022 · similarity 0.92)
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · similarity 0.91)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.90)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 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.
