Research map / Detection and segmentation / Open-set and few-shot detection
Retrieval Robust to Object Motion Blur
Rong Zou, Marc Pollefeys, Denys Rozumnyi
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 |
|---|---|---|---|
| train on motion-blurred images with blur-aware losses instead of sharp images only (ablation) | BRIDGE retrieval model · Synthetic blur-retrieval (no distractors) | mAP: 27.57 -> 91.78 | Improved |
| add localization loss (ablation) | L_con + L_cls · Synthetic (no distractors) | mAP: 85.06 -> 90.39 | Improved |
| add blur estimation loss (ablation) | L_con + L_cls · Synthetic (no distractors) | mAP: 85.06 -> 87.17 | Improved |
| add blur estimation loss on top of contrastive, classification and localization (ablation) | full loss · Synthetic (no distractors) | mAP: 90.39 -> 91.78 | Improved |
| add contrastive loss to cls + be + loc (ablation) | full loss · Synthetic (no distractors) | mAP: 91.23 -> 91.78 | Improved |
| add classification loss to con + be + loc (ablation) | full loss · Synthetic (no distractors) | mAP: 87.48 -> 91.78 | Improved |
| widen contrastive blur level range from 1 to 5 (ablation) | BLISS sample selection · Synthetic (+1M distractors) | mAP@100: 82.26 -> 84.09 | Improved |
| exclude edge pixels in blur severity (erosion) for blur estimation loss (ablation) | blur estimation loss · Synthetic (+1M distractors) | mAP@100: 82.83 -> 84.09 | Improved |
| use proposed method vs standard retrieval methods on real blurred data without fine-tuning | DELG, DOLG, Token baselines · Real-world blur-retrieval | mAP: 54.82 -> 62.88 | Improved |
| train only on sharp images (Ours-sharp) evaluated with distractors on query BL 1 (ablation) | BRIDGE · Synthetic (+1M distractors, query BL 1) | mAP@100: 71.93 (query BL 1) vs 32.64 overall | Mixed |
Closest papers by meaning
- Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (ECCV 2020 · similarity 0.86)
- Improved Handling of Motion Blur in Online Object Detection (CVPR 2021 · similarity 0.86)
- DeFMO: Deblurring and Shape Recovery of Fast Moving Objects (CVPR 2021 · similarity 0.85)
- OMoBlur: An Object Motion Blur Dataset and Benchmark for Real-World Local Motion Deblurring (CVPR 2026 · similarity 0.85)
- World From Blur (CVPR 2019 · similarity 0.85)
- Parametric Object Motion From Blur (CVPR 2016 · 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.
