Research map / Video / Video segmentation and tracking
Learning To Restore Hazy Video: A New Real-World Dataset and a New Method
Xinyi Zhang, Hang Dong, Jinshan Pan, Chao Zhu, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Fei Wang
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 |
|---|---|---|---|
| Train on REVIDE rather than REVIDE-SYN | CG-IDN · REVIDE test | PSNR: 15.02 -> 23.21 | Improved |
| Add deformable alignment to the three-frame baseline (ablation) | CG-IDN restoration backbone · REVIDE test | PSNR: 21.85 -> 22.42 | Improved |
| Add partial cost volume guidance to deformable alignment (ablation) | Baseline-DA · REVIDE test | PSNR: 22.42 -> 22.86 | Improved |
| Add confidence-guided pre-dehazing (CGPD) (ablation) | Baseline-IDA · REVIDE test | PSNR: 22.86 -> 23.08 | Improved |
| Add confidence-guided multi-feature fusion (MFF) (ablation) | Baseline-PD-IDA · REVIDE test | PSNR: 23.08 -> 23.21 | Improved |
| Use three input frames instead of one, without an alignment module (ablation) | CG-IDN restoration backbone · REVIDE test | PSNR: 21.81 -> 21.85 | No clear effect |
| Align neighboring frames with PWC-Net optical flow and warping (ablation) | Baseline-F3 · REVIDE test | PSNR: 21.85 -> 22.10 | Improved |
| Use the proposed CG-IDN rather than MSBDN | dehazing models trained on REVIDE · REVIDE test | PSNR: 22.01 -> 23.21 | Improved |
| Use the proposed CG-IDN rather than MSBDN | dehazing models trained on REVIDE · REVIDE test | SSIM: 0.8759 -> 0.8836 | Improved |
Closest papers by meaning
- Advancing Real-World Image Dehazing: Perspective, Modules, and Training (TPAMI 2024 · similarity 0.89)
- Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior (CVPR 2023 · similarity 0.89)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.88)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.87)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.87)
- Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing (CVPR 2024 · 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.
