Research map / 3D vision / NeRF and radiance fields
Deblur-NeRF: Neural Radiance Fields From Blurry Images
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Model blur during training with a deformable sparse kernel and jointly optimize a sharp NeRF | NeRF · Synthetic camera motion blur, 5-scene average | PSNR: 25.11 -> 28.77 | Helped |
| Model blur during training with a deformable sparse kernel and jointly optimize a sharp NeRF | NeRF · Synthetic defocus blur, 5-scene average | PSNR: 25.89 -> 28.37 | Helped |
| Add gamma correction (ablation) | Deblur-NeRF · Synthetic camera motion blur, 5-scene average | PSNR: 27.07 -> 28.77 | Helped |
| Add gamma correction (ablation) | Deblur-NeRF · Synthetic defocus blur, 5-scene average | PSNR: 27.29 -> 28.37 | Helped |
| Add alignment loss (ablation) | Deblur-NeRF · Synthetic camera motion blur, 5-scene average | PSNR: 25.48 -> 28.77 | Helped |
| Add alignment loss (ablation) | Deblur-NeRF · Synthetic defocus blur, 5-scene average | PSNR: 26.28 -> 28.37 | Helped |
| Add ray origin optimization (ablation) | Deblur-NeRF · Synthetic camera motion blur, 5-scene average | PSNR: 28.11 -> 28.77 | Helped |
| Add ray origin optimization (ablation) | Deblur-NeRF · Synthetic defocus blur, 5-scene average | PSNR: 28.13 -> 28.37 | Helped |
| Increase the number of sparse kernel points (ablation) | Deblur-NeRF · Synthetic blur situations, both blur types and three blur degrees | PSNR | Helped |
| Add positional encoding to the DSK MLP input (ablation) | Deblur-NeRF · Blurred image inputs | novel-view quality | No clear effect |
Closest papers by meaning
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.92)
- Exploiting Deblurring Networks for Radiance Fields (CVPR 2025 · similarity 0.91)
- LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes (NeurIPS 2024 · similarity 0.91)
- Mitigating Motion Blur in Neural Radiance Fields with Events and Frames (CVPR 2024 · similarity 0.91)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.90)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.90)
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.