Research map / 3D vision / NeRF and radiance fields
KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter
Yifan Zhan, Zhuoxiao Li, Muyao Niu, Zhihang Zhong, Shohei Nobuhara, Ko Nishino, Yinqiang Zheng
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 canonical observation loss L_co (ablation) | KFD-NeRF · synthetic and real average | PSNR (dB): 30.15 -> 31.78 | Improved |
| add estimation update loss L_kf (ablation) | KFD-NeRF · synthetic and real average | PSNR (dB): 30.15 -> 30.60 | Improved |
| combine L_kf and L_co (ablation) | KFD-NeRF · synthetic and real average | PSNR (dB): 31.78 -> 32.24 | Improved |
| add Kalman prediction branch (motion-equation prediction fused by Kalman gain) (ablation) | KFD-NeRF · Nvidia real data, dynamic areas | PSNR (dB): 25.61 -> 26.71 | Improved |
| feed previous two timestamps into a pure MLP instead of Kalman motion modeling (ablation) | pure observation MLP · Nvidia real data, dynamic areas | PSNR (dB): 25.61 -> 25.66 | No clear effect |
| add prediction branch for static areas (ablation) | KFD-NeRF · Nvidia real data, static areas | PSNR (dB): 29.58 -> 29.57 | No clear effect |
| use KFD-NeRF vs 4D-GS on perceptual quality in synthetic data | KFD-NeRF · D-NeRF synthetic dynamic scenes | LPIPS: 0.026 -> 0.045 vs 4D-GS | Hurt |
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
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · similarity 0.91)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 2024 · similarity 0.90)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.89)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.89)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.88)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.88)
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.
