Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.13258 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909039904948224 |
|---|---|
| author | Pan, Youwei Cao, Leilei Zhu, Yingfang Zhu, Fengjie |
| author_facet | Pan, Youwei Cao, Leilei Zhu, Yingfang Zhu, Fengjie |
| contents | In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the strong baseline framework X-Restormer, which effectively captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention). To further boost the restoration performance, we propose several key improvements. First, we integrate the spatially-adaptive input scaling mechanism from Restormer-Plus to dynamically adjust the spatial weights of the input image, enhancing spatial adaptability. Second, to better preserve structural details and edge information, we introduce a novel Gradient-Guided Edge-Aware (GGEA) loss, which is combined with L1 and Multi-Scale SSIM losses in a unified training objective. Third, we significantly expand the training data by incorporating an extra 24,500 degraded-clean image pairs from FoundIR and WeatherBench alongside the original WeatherStream dataset. With these strategies, our proposed method successfully ranks the 1st place in the challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13258 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge Pan, Youwei Cao, Leilei Zhu, Yingfang Zhu, Fengjie Computer Vision and Pattern Recognition Artificial Intelligence In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the strong baseline framework X-Restormer, which effectively captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention). To further boost the restoration performance, we propose several key improvements. First, we integrate the spatially-adaptive input scaling mechanism from Restormer-Plus to dynamically adjust the spatial weights of the input image, enhancing spatial adaptability. Second, to better preserve structural details and edge information, we introduce a novel Gradient-Guided Edge-Aware (GGEA) loss, which is combined with L1 and Multi-Scale SSIM losses in a unified training objective. Third, we significantly expand the training data by incorporating an extra 24,500 degraded-clean image pairs from FoundIR and WeatherBench alongside the original WeatherStream dataset. With these strategies, our proposed method successfully ranks the 1st place in the challenge. |
| title | X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.13258 |