Research map / Video / Video segmentation and tracking
ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
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 |
|---|---|---|---|
| Use ARVo instead of the strongest listed baseline | Video deblurring · DVD test | PSNR: 32.13 -> 32.80 | Helped |
| Use ARVo instead of the strongest listed baseline | Video deblurring · HFR-DVD test | PSNR: 29.71 -> 31.15 | Helped |
| Add correlation-volume features rather than using none (ablation) | ARVo · DVD test | PSNR: 31.85 -> 32.45 | Helped |
| Increase correlation-pyramid depth from 1 to 3 layers (ablation) | ARVo · DVD test | PSNR: 32.45 -> 32.80 | Helped |
| Increase correlation-pyramid depth from 3 to 4 layers (ablation) | ARVo · DVD test | PSNR: 32.80 -> 32.81 | No clear effect |
| Add optical-flow alignment to correlation-volume alignment (ablation) | ARVo · DVD test | PSNR: 32.01 -> 32.80 | Helped |
| Add correlation-volume alignment to optical-flow alignment (ablation) | ARVo · DVD test | PSNR: 31.85 -> 32.80 | Helped |
| Train progressively with 2 stages instead of 1 (ablation) | ARVo · DVD test | PSNR: 32.28 -> 32.80 | Helped |
| Train progressively with 3 stages instead of 2 (ablation) | ARVo · DVD test | SSIM: 0.9352 -> 0.9349 | Hurt |
| Add adversarial training (ablation) | ARVo · DVD test | PSNR: 32.80 -> 32.79 (-0.01) | No clear effect |
| Add adversarial training (ablation) | ARVo · DVD test | SSIM: 0.9352 -> 0.9354 (+0.02) | No clear effect |
Closest papers by meaning
- Deep Video Deblurring for Hand-Held Cameras (CVPR 2017 · similarity 0.89)
- GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring (NeurIPS 2024 · similarity 0.87)
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains (CVPR 2024 · similarity 0.87)
- Parameterized Blur Kernel Prior Learning for Local Motion Deblurring (CVPR 2025 · similarity 0.87)
- Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring (CVPR 2024 · similarity 0.87)
- Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos (NeurIPS 2025 · similarity 0.86)
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.