Research map / 3D vision / NeRF and radiance fields
URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fields
Bo Xu, Liu Ziao, Mengqi Guo, jiancheng Li, Gim Hee Lee
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 bundle adjustment to Tri-MipRF (ablation) | Tri-MipRF · Traj1-medium-large noise | PSNR: 15.24 -> 26.35 | Improved |
| add rolling shutter modeling with velocity estimation (ablation) | Tri-MipRF-BA · Traj1-medium-large noise | PSNR: 26.35 -> 27.16 | Improved |
| add coarse-to-fine strategy with outlier pose correction (ablation) | URS-NeRF · Traj1-medium-large noise | PSNR: 27.16 -> 29.37 | Improved |
| add coarse-to-fine strategy with outlier pose correction (ablation) | URS-NeRF · Traj1-medium-small noise | PSNR: 29.01 -> 29.34 | Improved |
| add bundle adjustment to NeRF (BARF) | NeRF · WHU-RS-Fast unordered | PSNR: 21.66 -> 16.27 | Hurt |
| use interpolation-based RS model (USB-NeRF-RE) on unordered images | Tri-MipRF · WHU-RS-Fast unordered | PSNR: 27.55 -> 16.91 versus URS-NeRF | Hurt |
| URS-NeRF versus USB-NeRF-RE on sequential data | URS-NeRF · WHU-RS-Fast sequential | PSNR: 29.07 -> 27.70 | No clear effect |
| increase camera motion speed | URS-NeRF · WHU-RS unordered | PSNR: 29.42 -> 27.55 (slow -> fast) | Hurt |
| add bundle adjustment to Tri-MipRF (ablation) | Tri-MipRF · WHU-RS Traj1-fast | training time (s): 543.29 -> 1010.88 | 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.
- Tri-MipRF — Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields (ICCV 2023) · better on 1 of 1 shared result
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
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields (ICLR 2024 · similarity 0.95)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.89)
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving (ICLR 2024 · similarity 0.89)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.89)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.89)
- LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes (NeurIPS 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.
