Multi-Weather Image Restoration via Histogram-Based Transformer Feature Enhancement
This addresses the need for automated image restoration in complex, mixed weather scenarios, particularly for autonomous driving, representing an incremental advance over single-weather models.
The paper tackles the problem of restoring images under mixed adverse weather conditions, which is critical for applications like autonomous driving, and proposes a model that achieves state-of-the-art performance on public datasets.
Currently, the mainstream restoration tasks under adverse weather conditions have predominantly focused on single-weather scenarios. However, in reality, multiple weather conditions always coexist and their degree of mixing is usually unknown. Under such complex and diverse weather conditions, single-weather restoration models struggle to meet practical demands. This is particularly critical in fields such as autonomous driving, where there is an urgent need for a model capable of effectively handling mixed weather conditions and enhancing image quality in an automated manner. In this paper, we propose a Task Sequence Generator module that, in conjunction with the Task Intra-patch Block, effectively extracts task-specific features embedded in degraded images. The Task Intra-patch Block introduces an external learnable sequence that aids the network in capturing task-specific information. Additionally, we employ a histogram-based transformer module as the backbone of our network, enabling the capture of both global and local dynamic range features. Our proposed model achieves state-of-the-art performance on public datasets.