CCST: Lightweight Criss-Cross Swin Transformer for Remote Sensing Image Super-Resolution Under Multi-Degradation Scenarios

Transformer-based methods excel in remote sensing image super-resolution (RSISR) due to their ability to capture abundant self-similarity textures and structural information, which are critical for restoring high-resolution (HR) details. However, the core component of these methods, the self-attention mechanism, requires substantial computational resources, resulting in a restriction of deployment on resource-constrained remote sensing (RS) devices. The redundant feature extraction and insufficient refinement of local features also cause a significant RSISR performance drop in multi-degradation scenarios, where RSI often suffers from optical blur and transmission noise caused by adverse imaging environments. To mitigate the above limitations, we present a lightweight criss-cross Swin Transformer (CCST) for blind RSISR. Concretely, we introduce criss-cross (CC) encoding into the self-attention mechanism to establish CC feature correlations of each pixel in an RSI. Along with the shifted window mechanism, repeated CC encoding indirectly builds global feature dependencies. Compared to the conventional self-attention mechanism that spans the entire window, the proposed CC self-attention mechanism drastically reduces computational overhead and feature redundancy while capturing more global information by using large-size windows. Furthermore, to enhance the ability of the RSISR model to extract local features while expanding its receptive field, we incorporate a gated feed-forward tiny network (GatedFFN) to integrate multiscale features and introduce gated coefficient learning (GCL) to adaptively filter redundant counterparts. The experimental results show that our CCST achieves superior performance with lower computational demand compared to state-of-the-art Transformer-based SR algorithms and traditional RSISR methods in multi-degradation scenarios.