Snow removal causes challenges due to its characteristic of complex degradations. To this end, targeted treatment of multi-scale snow degradations is critical for the network to learn effective snow removal. In order to handle the diverse scenes, we propose a multi-scale projection transformer (MSP-Former), which understands and covers a variety of snow degradation features in a multi-path manner, and integrates comprehensive scene context information for clean reconstruction via self-attention operation. For the local details of various snow degradations, the local capture module is introduced in parallel to assist in the rebuilding of a clean image. Such design achieves the SOTA performance on three desnowing benchmark datasets while costing the low parameters and computational complexity, providing a guarantee of practicality.
@article{arxiv.2207.05621,
title = {MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing},
author = {Sixiang Chen and Tian Ye and Yun Liu and Taodong Liao and Jingxia Jiang and Erkang Chen and Peng Chen},
journal= {arXiv preprint arXiv:2207.05621},
year = {2023}
}