Research map / 3D vision / NeRF and radiance fields
MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video
Minh-Quan Viet Bui, Jong-Min Park, Jihyong Oh, Munchurl Kim
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 Unsupervised Staticness Maximization loss L_sm (ablation) | dynamic NeRF baseline · Blurry iPhone ablation (avg) | mPSNR: 16.48 -> 16.85 | Improved |
| add L_lg local geometry variance distillation (ablation) | L_sm model without BRI/MDD · Blurry iPhone ablation (avg) | mPSNR: 16.85 -> 17.18 | Improved |
| replace L_lg with scale-invariant depth loss L_D (ablation) | L_sm model · Blurry iPhone ablation (avg) | mPSNR: 17.18 -> 15.13 | Hurt |
| add scale-invariant depth loss L_D instead of no geometry regularization (ablation) | L_sm model · Blurry iPhone ablation (avg) | mPSNR: 16.85 -> 15.13 | Hurt |
| add BRI stage (ablation) | L_sm + L_lg model · Blurry iPhone ablation (avg) | mPSNR: 17.18 -> 17.24 | Improved |
| use interleaved optimization in BRI instead of naive pose optimization (ablation) | BRI stage · Blurry iPhone ablation (avg) | mPSNR: 16.06 -> 17.24 | Improved |
| add BRI initialization before MDD (ablation) | MDD stage · Blurry iPhone ablation (avg) | mPSNR: 16.86 -> 17.33 | Improved |
| add MDD stage (ablation) | BRI model · Blurry iPhone ablation (avg) | mLPIPS: 0.413 -> 0.376 | Improved |
| use MDD deblurring instead of 2D GShiftNet preprocessing (ablation) | L_sm + L_lg model · Blurry iPhone ablation (avg) | mPSNR: 16.80 -> 17.18 | Improved |
| refine straight latent sharp rays (LORR) instead of bending them (ablation) | MDD stage · Blurry iPhone ablation (avg) | mSSIM: 0.533 -> 0.591 | Improved |
| add GMRP global motion-aware ray prediction (ablation) | MDD stage · Blurry iPhone ablation (avg) | mLPIPS: 0.403 -> 0.376 | Improved |
| use interleaved optimization in BRI (ablation) | camera pose refinement · Blurry iPhone camera pose error | rotation error (deg): 0.00914 -> 0.00871 | Improved |
Later papers that compared with this method
1 later accepted paper reports MoBluRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video (AAAI 2026 · better on 6 of 6 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DyBluRF — DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024) · better on 6 of 6 shared results
- HexPlane — HexPlane: A Fast Representation for Dynamic Scenes (CVPR 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
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.92)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.91)
- Mitigating Motion Blur in Neural Radiance Fields with Events and Frames (CVPR 2024 · similarity 0.89)
- Exploiting Deblurring Networks for Radiance Fields (CVPR 2025 · similarity 0.89)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- DetRF: Detachable Novel Views Synthesis of Dynamic Scenes Using Backdrop-Driven Neural Radiance Fields (AAAI 2025 · 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.
