Rain-by-snow weather removal is a specialized task in weather-degraded image
restoration aiming to eliminate coexisting rain streaks and snow particles. In
this paper, we propose RSFormer, an efficient and effective Transformer that
addresses this challenge. Initially, we explore the proximity of convolution
networks (ConvNets) and vision Transformers (ViTs) in hierarchical
architectures and experimentally find they perform approximately at intra-stage
feature learning. On this basis, we utilize a Transformer-like convolution
block (TCB) that replaces the computationally expensive self-attention while
preserving attention characteristics for adapting to input content. We also
demonstrate that cross-stage progression is critical for performance
improvement, and propose a global-local self-attention sampling mechanism
(GLASM) that down-/up-samples features while capturing both global and local
dependencies. Finally, we synthesize two novel rain-by-snow datasets,
RSCityScape and RS100K, to evaluate our proposed RSFormer. Extensive
experiments verify that RSFormer achieves the best trade-off between
performance and time-consumption compared to other restoration methods. For
instance, it outperforms Restormer with a 1.53% reduction in the number of
parameters and a 15.6% reduction in inference time. Datasets, source code and
pre-trained models are available at https://github.com/chdwyb/RSFormer.

RSFormer 是一种高效有力的 Transformer，专门用于消除受天气影响的图像中的雨迹和雪花，它通过将 ConvNets 和 Vision Transformers 在分层结构中的接近度结合起来，利用替代自注意力机制的 Transformer-like 卷积块 (TCB) 以适应输入内容，并提出了全局 - 本地自注意力采样机制 (GLASM)