Research map / 3D vision / NeRF and radiance fields
BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields
Peng Wang, Lingzhe Zhao, Ruijie Ma, Peidong Liu
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 |
|---|---|---|---|
| Jointly optimize the NeRF scene and camera motion trajectories while synthesizing blur from exposure-time views | BAD-NeRF · Deblur-NeRF synthetic, deblurring | PSNR: 27.50 -> 30.94 | Improved |
| Jointly optimize the NeRF scene and camera motion trajectories while synthesizing blur from exposure-time views | BAD-NeRF · Deblur-NeRF synthetic, novel view synthesis | PSNR: 27.04 -> 29.28 | Improved |
| Train Deblur-NeRF with estimated COLMAP poses rather than ground-truth poses | Deblur-NeRF · Deblur-NeRF synthetic, deblurring | PSNR: 27.95 -> 25.56 | Hurt |
| Optimize the camera motion as a sequence of independent poses rather than a spline trajectory (ablation) | BAD-NeRF · Deblur-NeRF synthetic | PSNR: 30.94 -> 29.99 | Hurt |
| Optimize the camera motion as a sequence of independent poses rather than a spline trajectory (ablation) | BAD-NeRF · MBA-VO | PSNR: 29.67 -> 28.86 | Hurt |
| Replace linear interpolation with cubic B-Spline trajectory modeling (ablation) | BAD-NeRF · Deblur-NeRF synthetic | PSNR: 30.94 -> 30.89 | No clear effect |
| Replace linear interpolation with cubic B-Spline trajectory modeling (ablation) | BAD-NeRF · MBA-VO | PSNR: 29.67 -> 29.93 | Improved |
| Increase the number of virtual exposure-time views (ablation) | BAD-NeRF · Cozy2room and Factory sequences | PSNR | Mixed |
| Use multi-view NeRF information instead of relying on a single-image deblurring network | BAD-NeRF · Severely blurred images | LPIPS | Improved |
Later papers that compared with this method
6 later accepted papers report BAD-NeRF as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events (CVPR 2026 · better on 1 of 1 shared result)
- EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images (ICCV 2025 · better on 3 of 3 shared results)
- BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting (ECCV 2024 · better on 5 of 7 shared results)
- Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion (ECCV 2024 · better on 4 of 5 shared results)
- RaFE: Generative Radiance Fields Restoration (ECCV 2024 · better on 1 of 3 shared results)
- ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images (ICCV 2023 · better on 3 of 3 shared results)
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.
- Deblur-NeRF* — Deblur-NeRF: Neural Radiance Fields From Blurry Images (CVPR 2022) · better on 3 of 3 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
- Deblur-NeRF: Neural Radiance Fields From Blurry Images (CVPR 2022 · similarity 0.94)
- LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes (NeurIPS 2024 · similarity 0.92)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.91)
- Mitigating Motion Blur in Neural Radiance Fields with Events and Frames (CVPR 2024 · similarity 0.91)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.90)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 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.
