Research map / Video / Video segmentation and tracking
Simultaneous Stereo Video Deblurring and Scene Flow Estimation
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 |
|---|---|---|---|
| Jointly estimate scene flow and deblur images | Stereo video deblurring and scene flow · Blurred KITTI | flow error left (%): 13.62 -> 10.01 | Helped |
| Jointly estimate scene flow and deblur images | Stereo video deblurring and scene flow · Blurred KITTI | PSNR left: 28.25 -> 29.80 | Helped |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · Blurred KITTI | flow error right (%): 19.34 -> 11.45 | Mixed |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · Blurred KITTI | PSNR left: 30.24 -> 29.80 | Hurt |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · 50 challenging Blurred KITTI sequences | flow error right (%): 13.06 -> 6.17 | Helped |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · 50 challenging Blurred KITTI sequences | PSNR left: 32.22 -> 31.80 | Hurt |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · Chair | flow error (%): 1.22 -> 1.18 | Helped |
| Use three stereo frame pairs rather than two (ablation) | Proposed joint method · Chair | PSNR (dB): 23.13 -> 23.26 | Helped |
| Iterate between scene flow estimation and deblurring (ablation) | Proposed joint method · 50 challenging sequences | PSNR: +0.3dB | Helped |
| Replace the proposed joint method with stereo deblurring baseline | Chair scene flow and deblurring · Chair | flow error (%): 2.13 -> 1.18 | Helped |
Closest papers by meaning
- Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion (CVPR 2021 · similarity 0.88)
- DAVANet: Stereo Deblurring With View Aggregation (CVPR 2019 · similarity 0.88)
- Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring (CVPR 2024 · similarity 0.86)
- Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization (CVPR 2024 · similarity 0.85)
- Zero-Shot Monocular Scene Flow Estimation in the Wild (CVPR 2025 · similarity 0.85)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · 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.