Research map / Video / Action recognition
End-to-End United Video Dehazing and Detection
Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng
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 |
|---|---|---|---|
| Use five-frame K-level fusion at conv2 rather than the strongest listed image-based dehazing baseline | AOD-Net on TestSet V1 · TestSet V1 | PSNR: 20.6828 -> 20.9908 | Improved |
| Use five-frame K-level fusion at conv2 rather than the strongest listed baseline for SSIM | CAP on TestSet V1 · TestSet V1 | SSIM: 0.8848 -> 0.9087 | Improved |
| Jointly train video dehazing and video detection instead of using the best listed detection baseline | JAOD-Faster R-CNN on TestSet V2 · TestSet V2 | MAP: 0.758 -> 0.802 | Improved |
| Fuse five-frame inputs at conv2 rather than at the input or output level (ablation) | EVD-Net · TestSet V1 | PSNR: I-level fusion, 5 frames: 20.6095; J-level fusion, 5 frames: 20.3675; K-level fusion, conv2, 5 frames: 20.9908 | Improved |
| Use five rather than three frames for K-level fusion at conv2 (ablation) | EVD-Net · TestSet V1 | PSNR: 20.6998 -> 20.9908 | Improved |
| Use seven or nine rather than five frames for K-level fusion at conv2 (ablation) | EVD-Net · TestSet V1 | PSNR: 20.9908 -> 20.7901; 20.9908 -> 20.7355 | Hurt |
| Move the K-level fusion point from conv2 to conv3 while using five frames (ablation) | EVD-Net · TestSet V1 | PSNR: 20.9908 -> 20.7780 | Hurt |
| Move the K-level fusion point from conv2 to conv1 while using five frames (ablation) | EVD-Net · TestSet V1 | PSNR: 20.9908 -> 20.8240 | Hurt |
| Move the K-level fusion point from conv2 to conv4 or conv5(K) while using five frames (ablation) | EVD-Net · TestSet V1 | PSNR: 20.9908 -> 20.6756; 20.9908 -> 20.7942 | Hurt |
Closest papers by meaning
- Learning To Restore Hazy Video: A New Real-World Dataset and a New Method (CVPR 2021 · similarity 0.87)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior (CVPR 2020 · similarity 0.86)
- AOD-Net: All-In-One Dehazing Network (ICCV 2017 · similarity 0.86)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-Local Spatial-Temporal Similarity (TPAMI 2023 · similarity 0.86)
- Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing (AAAI 2025 · similarity 0.84)
- Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing (CVPR 2024 · 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.
