Research map / Image generation / Image restoration
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
Boyun Li, Yuanbiao Gou, Shuhang Gu, Jerry Zitao Liu, Joey Tianyi Zhou, Xi Peng
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 L_H (hint loss) for A-Net (ablation) | YOLY · HSTS synthetic outdoor | PSNR: 21.16 -> 23.82 | Improved |
| add L_KL (variational inference) for A-Net (ablation) | YOLY · HSTS synthetic outdoor | PSNR: 21.68 -> 23.82 | Improved |
| add L_J (brightness-saturation prior) for J-Net (ablation) | YOLY · HSTS synthetic outdoor | PSNR: 22.53 -> 23.82 | Improved |
| add L_Reg smoothness regularization on atmospheric light (ablation) | YOLY · HSTS synthetic outdoor | PSNR: 22.28 -> 23.82 | Improved |
| use YOLY instead of best unsupervised deep baseline DDIP (ablation) | unsupervised dehazing · SOTS indoor (synthetic) | PSNR: 16.97 -> 19.41 | Improved |
| use YOLY instead of DDIP | unsupervised dehazing · HSTS synthetic outdoor | PSNR: 20.91 -> 23.82 | Improved |
| compare YOLY with supervised DehazeNet | dehazing · SOTS indoor (synthetic) | PSNR: 21.14 -> 19.41 | Hurt |
| compare YOLY with supervised DehazeNet | dehazing · HSTS synthetic outdoor | PSNR: 24.48 -> 23.82 | Hurt |
| use YOLY instead of best prior-based method | dehazing · HSTS synthetic outdoor | PSNR: 18.92 -> 23.82 | Improved |
Closest papers by meaning
- Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training (AAAI 2018 · similarity 0.91)
- Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning (ECCV 2022 · similarity 0.90)
- Towards Multi-Domain Single Image Dehazing via Test-Time Training (CVPR 2022 · similarity 0.90)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.88)
- SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency (AAAI 2024 · similarity 0.87)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.87)
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.
