Research map / 3D vision / Depth and stereo
Light Field Blind Motion Deblurring
Pratul P. Srinivasan, Ren Ng, Ravi Ramamoorthi
Check 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 |
|---|---|---|---|
| Estimate a shared 3D camera motion path and sharp light field using the light-field forward model | Light Field Blind Motion Deblurring · Synthetic motion-blurred light fields | RMSE | Improved |
| Estimate a shared 3D camera motion path and sharp light field using the light-field forward model | Light Field Blind Motion Deblurring · Real handheld motion-blurred light fields | blur correction | Improved |
| Use 4D light-field deconvolution instead of 2D deconvolution | Deblurring a light field with known in-plane camera motion · Synthetic light fields with increasing linear in-plane motion | central sub-aperture image RMSE | Improved |
| Use light-field structure and estimate one shared 3D motion path rather than deblurring sub-aperture images independently | Light Field Blind Motion Deblurring · Synthetic and real motion-blurred light fields | angular consistency | Improved |
| Capture a 4D light field rather than a conventional 2D image | Motion deblurring under general 3D scene depth · In-plane camera motion | depth-independent deconvolution | Improved |
| Use a light field rather than a conventional 2D image | Blind deblurring of a single fronto-parallel textured plane under out-of-plane motion · Out-of-plane camera motion | texture recovery | Improved |
Closest papers by meaning
- Joint Blind Motion Deblurring and Depth Estimation of Light Field (ECCV 2018 · similarity 0.92)
- Divide and Conquer for Full-Resolution Light Field Deblurring (CVPR 2018 · similarity 0.92)
- OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring (CVPR 2026 · similarity 0.86)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.86)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.85)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.85)
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.
