WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912587402182656 |
|---|---|
| author | Guan, Qiyuan Yang, Qianfeng Chen, Xiang Song, Tianyu Jin, Guiyue Jin, Jiyu |
| author_facet | Guan, Qiyuan Yang, Qianfeng Chen, Xiang Song, Tianyu Jin, Guiyue Jin, Jiyu |
| contents | Existing all-in-one image restoration approaches, which aim to handle multiple weather degradations within a single framework, are predominantly trained and evaluated using mixed single-weather synthetic datasets. However, these datasets often differ significantly in resolution, style, and domain characteristics, leading to substantial domain gaps that hinder the development and fair evaluation of unified models. Furthermore, the lack of a large-scale, real-world all-in-one weather restoration dataset remains a critical bottleneck in advancing this field. To address these limitations, we present a real-world all-in-one adverse weather image restoration benchmark dataset, which contains image pairs captured under various weather conditions, including rain, snow, and haze, as well as diverse outdoor scenes and illumination settings. The resulting dataset provides precisely aligned degraded and clean images, enabling supervised learning and rigorous evaluation. We conduct comprehensive experiments by benchmarking a variety of task-specific, task-general, and all-in-one restoration methods on our dataset. Our dataset offers a valuable foundation for advancing robust and practical all-in-one image restoration in real-world scenarios. The dataset has been publicly released and is available at https://github.com/guanqiyuan/WeatherBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11642 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration Guan, Qiyuan Yang, Qianfeng Chen, Xiang Song, Tianyu Jin, Guiyue Jin, Jiyu Computer Vision and Pattern Recognition Existing all-in-one image restoration approaches, which aim to handle multiple weather degradations within a single framework, are predominantly trained and evaluated using mixed single-weather synthetic datasets. However, these datasets often differ significantly in resolution, style, and domain characteristics, leading to substantial domain gaps that hinder the development and fair evaluation of unified models. Furthermore, the lack of a large-scale, real-world all-in-one weather restoration dataset remains a critical bottleneck in advancing this field. To address these limitations, we present a real-world all-in-one adverse weather image restoration benchmark dataset, which contains image pairs captured under various weather conditions, including rain, snow, and haze, as well as diverse outdoor scenes and illumination settings. The resulting dataset provides precisely aligned degraded and clean images, enabling supervised learning and rigorous evaluation. We conduct comprehensive experiments by benchmarking a variety of task-specific, task-general, and all-in-one restoration methods on our dataset. Our dataset offers a valuable foundation for advancing robust and practical all-in-one image restoration in real-world scenarios. The dataset has been publicly released and is available at https://github.com/guanqiyuan/WeatherBench. |
| title | WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.11642 |