Research map / Detection and segmentation / CNN features
Blur-Robust Detection via Feature Restoration: An End-to-End Framework for Prior-Guided Infrared UAV Target Detection
Xiaolin Wang, Houzhang Fang, Qingshan Li, Lu Wang, Yi Chang, Luxin Yan
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 |
|---|---|---|---|
| add feature-domain deblurring (FDD) to DEIM (ablation) | DEIM · IRBlurUAV-syn | AP: 0.290 -> 0.390 | Improved |
| add frequency structure guidance module (FSGM) on top of FDD (ablation) | JFD3 · IRBlurUAV-syn | AP: 0.390 -> 0.420 | Improved |
| add FSGM on top of FDD (ablation) | JFD3 · IRBlurUAV-syn | AP50: 0.763 -> 0.765 | No clear effect |
| add image-domain deblurring (DeepRFT) before JFD3 in addition to FDD (ablation) | JFD3 · IRBlurUAV-syn | AP50: 0.763 -> 0.703 | Hurt |
| joint feature-domain training instead of DeepRFT image deblurring plus detector (ablation) | D-FINE/RT-DETR · IRBlurUAV-syn | AP50: 0.660 -> 0.763 | Improved |
| prepend deblurring (DeepRFT) to detector instead of direct detection | D-FINE · IRBlurUAV-syn | AP50: 0.722 -> 0.660 | Hurt |
| prepend MDT/MaIR deblurring to detector | RT-DETR · IRBlurUAV-syn | AP50: 0.716 -> 0.195 (MDT) | Hurt |
| JFD3 versus DeepRFT+RT-DETR across blur levels | JFD3 · IRBlurUAV-syn | AP50: 0.542 -> 0.562 (severe); 0.772 vs 0.767 (mild) | Mixed |
| JFD3 versus direct D-FINE on real blurred images | JFD3 · IRBlurUAV-real | AP50: 0.514 -> 0.623 | Improved |
| add FDD to restore shallow backbone features (ablation) | JFD3 · Stage1 feature PSNR | PSNR: 15.29 -> 18.18 | Improved |
Closest papers by meaning
- Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAV Target Detection (CVPR 2025 · similarity 0.87)
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm (NeurIPS 2026 · similarity 0.84)
- Rethinking Evaluation of Infrared Small Target Detection (NeurIPS 2025 · similarity 0.83)
- Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy (NeurIPS 2025 · similarity 0.83)
- FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection (AAAI 2025 · similarity 0.83)
- RemDet: Rethinking Efficient Model Design for UAV Object Detection (AAAI 2025 · similarity 0.83)
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.
