MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing
This work addresses snow removal in images, which is a domain-specific problem for computer vision applications, and appears incremental as it builds on existing transformer and multi-scale methods.
The paper tackles the problem of single image desnowing by proposing MSP-Former, a multi-scale projection transformer that handles complex snow degradations, achieving state-of-the-art performance on three benchmark datasets with low parameters and computational complexity.
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.