Research map / Video / Video segmentation and tracking
Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior
Jiaqi Xu, Xiaowei Hu, Lei Zhu, Qi Dou, Jifeng Dai, Yu Qiao, Pheng-Ann Heng
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 memory-based physical prior guidance (MPG) module (ablation) | base video dehazing network · HazeWorld | PSNR: +0.87 dB (25.37 to 26.24) | Improved |
| add multi-range scene radiance recovery (MSR) module (ablation) | base video dehazing network · HazeWorld | PSNR: +1.01 dB (25.37 to 26.38) | Improved |
| add prior guidance to STDA block only (ablation) | MSR module · HazeWorld | PSNR: +0.54 dB (26.38 to 26.92) | Improved |
| add prior guidance to GMRA block only (ablation) | MSR module · HazeWorld | PSNR: +0.23 dB (26.38 to 26.61) | Improved |
| use 3 space-time ranges instead of 1, 2 or 4 (ablation) | MSR module · HazeWorld | PSNR: 27.12 vs 26.24 (1 range), 26.71 (2), 26.84 (4) | Mixed |
| multi-range sets vs single set of three frames (ablation) | MSR temporal alignment · HazeWorld | PSNR: +0.73 dB (26.39 to 27.12) | Improved |
| multi-range sets vs frame-by-frame alignment (3sets-1range) (ablation) | MSR temporal alignment · HazeWorld | PSNR: +0.48 dB (26.64 to 27.12) | Improved |
| full MAP-Net vs image and video baselines | video dehazing · HazeWorld | PSNR: +1.06 dB over BasicVSR++ (26.06) | Improved |
| full MAP-Net vs NCFL on REVIDE | video dehazing · REVIDE | PSNR: +0.53 dB (23.63 to 24.16) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BasicVSR++ — BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video (AAAI 2025 · similarity 0.87)
- LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing (NeurIPS 2026 · similarity 0.87)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.87)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.86)
- Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance (CVPR 2024 · similarity 0.86)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 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.
