Research map / Image generation / Image restoration
All in One Bad Weather Removal Using Architectural Search
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the all-in-one network instead of HRGAN | Bad weather removal on Test 1 · Test 1 [25] | PSNR: 21.56 -> 24.71 | Helped |
| Use the all-in-one network instead of HRGAN | Bad weather removal on Test 1 · Test 1 [25] | SSIM: 0.855 -> 0.898 | Helped |
| Use the all-in-one network instead of Quan et al. | Raindrop removal · Raindrop [41] | PSNR: 31.44 -> 31.12 | Hurt |
| Use the all-in-one network instead of Quan et al. | Raindrop removal · Raindrop [41] | SSIM: 0.9263 -> 0.9268 | Helped |
| Use the all-in-one network instead of DesnowNet | Snow removal · Snow100K-L test | PSNR: 27.17 -> 28.33 | Helped |
| Use the all-in-one network instead of DesnowNet | Snow removal · Snow100K-L test | SSIM: 0.8983 -> 0.8820 | Hurt |
| Add feature search (ablation) | All-in-one network on the rain and fog test dataset · Test 1 [25] | PSNR: 20.82 -> 24.71 | Helped |
| Add feature search (ablation) | All-in-one network on the rain and fog test dataset · Test 1 [25] | SSIM: 0.827 -> 0.898 | Helped |
| Add the categorical discriminator (ablation) | All-in-one network on the rain and fog test dataset · Test 1 [25] | PSNR: 21.58 -> 24.71 | Helped |
| Add the categorical discriminator (ablation) | All-in-one network on the rain and fog test dataset · Test 1 [25] | SSIM: 0.86 -> 0.898 | Helped |
Closest papers by meaning
- Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions (CVPR 2023 · similarity 0.91)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.87)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.87)
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.87)
- Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start (NeurIPS 2025 · similarity 0.87)
- Boosting Image De-Raining via Central-Surrounding Synergistic Convolution (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.