Vision Transformer with Key-select Routing Attention for Single Image Dehazing

This work addresses image quality improvement for computer vision applications, but appears incremental as it builds on existing transformer-based approaches.

The paper tackles single image dehazing by proposing Ksformer, which uses Multi-scale Key-select Routing Attention to intelligently select key areas and a Lightweight Frequency Processing Module to enhance high-frequency features, outperforming other methods in tests.