Research map / Image generation / Image restoration
Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and a New Physics-Inspired Transformer Model
Zhiyuan Mao, Ajay Jaiswal, Zhangyang Wang, Stanley H. Chan
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 turbulence map estimation (degradation block with self-supervised loss) (ablation) | TurbNet · Heat Chamber | PSNR: 19.03 -> 19.76 | Improved |
| add turbulence map estimation (degradation block with self-supervised loss) (ablation) | TurbNet · Heat Chamber | SSIM: 0.6852 -> 0.6934 | Improved |
| use transformer encoder instead of U-Net (ablation) | TurbNet · Heat Chamber | PSNR: 18.62 -> 19.76 | Improved |
| use transformer encoder instead of U-Net (ablation) | TurbNet · Heat Chamber | SSIM: 0.6481 -> 0.6934 | Improved |
| restore with TurbNet before OCR | OCR pipeline · Turbulence Text Dataset | AWDR: 0.623 -> 0.758 | Improved |
| restore with TurbNet before OCR | OCR pipeline · Turbulence Text Dataset | AD-LCS: 5.076 -> 7.314 | Improved |
| restore with TDRN before OCR | OCR pipeline · Turbulence Text Dataset | AWDR: 0.623 -> 0.617 | Hurt |
| use TurbNet instead of Restormer | TurbNet · Synthetic turbulence test | PSNR: 22.29 -> 22.76 | Improved |
| use TurbNet instead of Restormer | TurbNet · Turbulence Text Dataset | AD-LCS: 6.226 -> 7.314 | 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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 6 of 6 shared results
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
- Spatio-Temporal Turbulence Mitigation: A Translational Perspective (CVPR 2024 · similarity 0.89)
- Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence (CVPR 2024 · similarity 0.88)
- Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation (CVPR 2025 · similarity 0.88)
- NB-GTR: Narrow-Band Guided Turbulence Removal (CVPR 2024 · similarity 0.87)
- Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations (NeurIPS 2024 · similarity 0.86)
- Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation (CVPR 2024 · 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.
