Research map / 3D vision / Depth and stereo
Joint Blind Motion Deblurring and Depth Estimation of Light Field
Dongwoo Lee, Haesol Park, In Kyu Park, Kyoung Mu Lee
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 |
|---|---|---|---|
| joint estimation of latent image, depth and 6-DOF motion vs Sun et al. CNN-based deblurring | Sun et al. · Synthetic light field deblurring (Forward) | PSNR: 27.69 -> 29.24 | Improved |
| joint estimation vs Sun et al. | Sun et al. · Synthetic light field deblurring (Translation) | PSNR: 25.41 -> 26.99 | Improved |
| joint estimation vs Hu et al. global motion model | Hu et al. · Synthetic light field deblurring (Forward) | PSNR: 20.00 -> 29.24 | Improved |
| joint estimation vs Srinivasan et al. on cropped light fields | Srinivasan et al. · Synthetic light field deblurring (Forward, cropped) | PSNR: 17.15 -> 27.15 | Improved |
| jointly estimate depth with deblurring instead of independently deblurring sub-aperture images (ablation) | Chen et al. depth estimation · Light field depth estimation (overall) | L1-rel error: 0.0303 -> 0.0197 | Improved |
| jointly estimate depth with deblurring vs Jeon et al. on independently deblurred images (ablation) | Jeon et al. · Light field depth estimation (overall) | L1-rel error: 0.0891 -> 0.0197 | Improved |
| 6-DOF camera motion model vs linear blur kernels | Sun et al. · Camera motion estimation (Rotation) | EPE: 2.557 -> 0.171 | Improved |
| 6-DOF camera motion model vs linear blur kernels | Sun et al. · Camera motion estimation (Forward) | EPE: 1.492 -> 0.325 | Improved |
| initialize motion from local linear kernels and depth with RANSAC vs Sun et al. | Sun et al. · Synthetic motion initialization | EPE: 3.05 -> 0.95 | Improved |
Closest papers by meaning
- Light Field Blind Motion Deblurring (CVPR 2017 · similarity 0.92)
- Divide and Conquer for Full-Resolution Light Field Deblurring (CVPR 2018 · similarity 0.91)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · similarity 0.87)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.86)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 2024 · similarity 0.85)
- Exploiting Deblurring Networks for Radiance Fields (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.
