Research map / 3D vision / Depth and stereo
World From Blur
Jiayan Qiu, Xinchao Wang, Stephen J. Maybank, Dacheng Tao
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 |
|---|---|---|---|
| Add the self-supervised reconstruction cycle to motion estimation (ablation) | World From Blur · NYU Depth v2 test | Translationx error (cm): 3.589 -> 2.584 | Improved |
| Add the self-supervised reconstruction cycle to motion estimation (ablation) | World From Blur · ICL-NUIM test | Translationx error (cm): 3.813 -> 2.961 | Improved |
| Add the self-supervised reconstruction cycle to deblurring (ablation) | World From Blur · NYU Depth v2 test | PSNR: 25.94 -> 27.22 | Improved |
| Add the self-supervised reconstruction cycle to deblurring (ablation) | World From Blur · ICL-NUIM test | PSNR: 26.43 -> 27.19 | Improved |
| Add the self-supervised reconstruction cycle to depth estimation (ablation) | World From Blur · NYU Depth v2 test | Abs Rel: 0.217 -> 0.184 | Improved |
| Add the self-supervised reconstruction cycle to depth estimation (ablation) | World From Blur · ICL-NUIM test | Abs Rel: 0.220 -> 0.206 | Improved |
| Use the two-branch depth network instead of Eigen's depth network in the cycle (ablation) | World From Blur self-supervised cycle · NYU Depth v2 test | Abs Rel: 0.198 -> 0.184 | Improved |
| Use the two-branch depth network instead of Eigen's depth network in the cycle (ablation) | World From Blur self-supervised cycle · NYU Depth v2 test | PSNR: 26.13 -> 27.22 | Improved |
Closest papers by meaning
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (CVPR 2017 · similarity 0.89)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.89)
- Stereo Video Deblurring (ECCV 2016 · similarity 0.88)
- OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring (CVPR 2026 · similarity 0.88)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.87)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.87)
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.
