WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration
This addresses a critical bottleneck for researchers in computer vision by providing a standardized real-world dataset to advance robust all-in-one image restoration, though it is incremental as it focuses on dataset creation rather than a new method.
The authors tackled the lack of a real-world benchmark for all-in-one adverse weather image restoration by introducing WeatherBench, a dataset with aligned degraded and clean images across rain, snow, and haze, enabling supervised learning and evaluation of various methods.
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.