Research map / 3D vision / NeRF and radiance fields
BARF: Bundle-Adjusting Neural Radiance Fields
Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, Simon Lucey
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 coarse-to-fine positional encoding schedule (BARF) instead of naive full encoding (ablation) | NeRF · Planar image alignment | sl(3) error: 0.2949 -> 0.0096 | Improved |
| add coarse-to-fine positional encoding schedule (BARF) instead of naive full encoding (ablation) | NeRF · Planar image alignment | patch PSNR: 23.41 -> 35.30 | Improved |
| add coarse-to-fine schedule (BARF) instead of no positional encoding (ablation) | NeRF · Planar image alignment | patch PSNR: 24.72 -> 35.30 | Improved |
| use coarse-to-fine encoding instead of naive full positional encoding (ablation) | NeRF · NeRF synthetic mean, perturbed poses | rotation error (deg): 6.167 -> 0.193 | Improved |
| use coarse-to-fine encoding instead of naive full positional encoding (ablation) | NeRF · NeRF synthetic mean, perturbed poses | PSNR: 22.12 -> 27.50 | Improved |
| use coarse-to-fine encoding instead of no positional encoding (ablation) | NeRF · NeRF synthetic mean, perturbed poses | PSNR: 26.78 -> 27.50 | Improved |
| use coarse-to-fine encoding instead of no positional encoding (ablation) | NeRF · NeRF synthetic mean, perturbed poses | rotation error (deg): 0.202 -> 0.193 | No clear effect |
| use coarse-to-fine encoding instead of naive full positional encoding (ablation) | NeRF · LLFF unknown poses mean | rotation error (deg): 84.509 -> 0.573 | Improved |
| use coarse-to-fine encoding instead of naive full positional encoding (ablation) | NeRF · LLFF unknown poses mean | PSNR: 11.03 -> 23.97 | Improved |
| use coarse-to-fine encoding instead of no positional encoding (ablation) | NeRF · LLFF unknown poses mean | PSNR: 23.82 -> 23.97 | Mixed |
| use coarse-to-fine encoding instead of no positional encoding (ablation) | NeRF · LLFF unknown poses mean | rotation error (deg): 0.699 -> 0.573 | Mixed |
| sample points in metric depth instead of inverse depth | BARF · LLFF unknown poses mean | rotation error (deg): 0.573 -> 1.580 | Hurt |
Later papers that compared with this method
19 later accepted papers report BARF as a baseline in their results tables; 19 of them report a better number on most of the results they share with it.
- Energy-GS: Image Energy-guided Pose Alignment Gaussian Splatting with redesigned pose gradient flow (CVPR 2026 · better on 8 of 8 shared results)
- Reconstructing Satellites in 3D From Amateur Telescope Images (TPAMI 2025 · better on 5 of 5 shared results)
- GFlow: Recovering 4D World from Monocular Video (AAAI 2025 · better on 3 of 3 shared results)
- PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations (ICCV 2025 · better on 2 of 2 shared results)
- Invertible Neural Warp for NeRF (ECCV 2024 · better on 11 of 11 shared results)
- Continuous Pose for Monocular Cameras in Neural Implicit Representation (CVPR 2024 · better on 6 of 6 shared results)
- ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization (CVPR 2024 · better on 3 of 3 shared results)
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields (ICLR 2024 · better on 3 of 3 shared results)
11 more not listed.
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
- Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields (CVPR 2023 · similarity 0.93)
- DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields (CVPR 2023 · similarity 0.92)
- AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training (CVPR 2023 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.89)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 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.
