Research map / Architectures and efficiency / Attention and transformers
TransWeather: Transformer-Based Restoration of Images Degraded by Adverse Weather Conditions
Jeya Maria Jose Valanarasu, Rajeev Yasarla, Vishal M. Patel
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 |
|---|---|---|---|
| Use TransWeather instead of All-in-One | All-in-One adverse-weather restoration · Test1 (rain+fog) | PSNR: 24.71 -> 27.96 | Improved |
| Use TransWeather instead of All-in-One | All-in-One adverse-weather restoration · Snow100K-L | SSIM: 0.8820 -> 0.9308 | Improved |
| Use TransWeather instead of All-in-One | All-in-One adverse-weather restoration · RainDrop test | PSNR: 31.12 -> 28.84 | Hurt |
| Use TransWeather instead of All-in-One | All-in-One adverse-weather restoration · RainDrop test | SSIM: 0.9268 -> 0.9460 | Improved |
| Add a hierarchical encoder (ablation) | Transformer Base · RainDrop test | PSNR: 30.12 -> 31.62 | Improved |
| Add a hierarchical encoder (ablation) | Transformer Base · RainDrop test | SSIM: 0.8512 -> 0.8671 | Improved |
| Add Intra-PT blocks to the hierarchical encoder (ablation) | Hierarchical encoder · RainDrop test | PSNR: 31.62 -> 32.37 | Improved |
| Add Intra-PT blocks to the hierarchical encoder (ablation) | Hierarchical encoder · RainDrop test | SSIM: 0.8671 -> 0.9463 | Improved |
| Add learnable weather queries and a transformer decoder (ablation) | Hierarchical encoder with Intra-PT · RainDrop test | PSNR: 32.37 -> 34.55 | Improved |
| Add learnable weather queries and a transformer decoder (ablation) | Hierarchical encoder with Intra-PT · RainDrop test | SSIM: 0.9463 -> 0.9502 | Improved |
| Use TransWeather instead of DDMSNET | Snow removal · Snow100K-L | PSNR: 28.85 -> 28.48 | Hurt |
| Use TransWeather instead of Quan et al. | Raindrop removal · RainDrop test | PSNR: 31.44 -> 28.84 | Hurt |
Later papers that compared with this method
1 later accepted paper reports TransWeather as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions (IJCV 2024 · 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
- Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal (CVPR 2024 · similarity 0.88)
- AWRaCLe: All-Weather Image Restoration Using Visual In-Context Learning (AAAI 2025 · similarity 0.85)
- Language-driven All-in-one Adverse Weather Removal (CVPR 2024 · similarity 0.85)
- Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining (CVPR 2024 · similarity 0.85)
- Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration (AAAI 2025 · similarity 0.85)
- Towards Universal Rainy Image Restoration: Benchmark and Baseline (AAAI 2025 · 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.
