Research map / Label-efficient and robust learning / Test-time adaptation
Towards Multi-Domain Single Image Dehazing via Test-Time Training
Huan Liu, Zijun Wu, Liangyan Li, Sadaf Salehkalaibar, Jun Chen, Keyan 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 |
|---|---|---|---|
| Apply proposed test-time training to multi-domain GDN | GDN · RESIDE indoor SOTS | PSNR: 26.67 -> 26.83 | Improved |
| Apply proposed test-time training to multi-domain GDN | GDN · RESIDE outdoor SOTS | PSNR: 27.18 -> 27.26 | Improved |
| Apply proposed test-time training to multi-domain GDN | GDN · O-Haze | PSNR: 23.13 -> 23.21 | Improved |
| Apply proposed test-time training to multi-domain GDN | GDN · NH-Haze | PSNR: 18.93 -> 19.04 | Improved |
| Use helper-network test-time supervision without meta-learning (ablation) | GDN · RESIDE indoor SOTS | PSNR: 26.67 -> 26.69 | Improved |
| Use helper-network test-time supervision without meta-learning (ablation) | GDN · RESIDE outdoor SOTS | PSNR: 27.18 -> 27.16 | Hurt |
| Use helper-network test-time supervision without meta-learning (ablation) | GDN · O-Haze | PSNR: 23.13 -> 22.89 | Hurt |
| Use helper-network test-time supervision without meta-learning (ablation) | GDN · NH-Haze | PSNR: 18.93 -> 18.65 | Hurt |
| Jointly train GDN with dehazing and haze-reconstruction losses (ablation) | GDN + Helper · RESIDE indoor SOTS | PSNR: 26.67 -> 26.71 | Improved |
| Jointly train GDN with dehazing and haze-reconstruction losses (ablation) | GDN + Helper · RESIDE outdoor SOTS | PSNR: 27.18 -> 27.19 | Improved |
| Jointly train GDN with dehazing and haze-reconstruction losses (ablation) | GDN + Helper · O-Haze | PSNR: 23.13 -> 22.94 | Hurt |
| Jointly train GDN with dehazing and haze-reconstruction losses (ablation) | GDN + Helper · NH-Haze | PSNR: 18.93 -> 18.71 | Hurt |
Closest papers by meaning
- Prompt-Based Test-Time Real Image Dehazing: A Novel Pipeline (ECCV 2024 · similarity 0.90)
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network (IJCV 2021 · similarity 0.90)
- Advancing Real-World Image Dehazing: Perspective, Modules, and Training (TPAMI 2024 · similarity 0.90)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.88)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.88)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (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.
