MSST-Net: Memory-Sustained Structure-Texture Representation Network for Remote Sensing Building Change Detection

Building change detection in remote sensing plays an important role in urban planning, land-use monitoring, and rapid postdisaster damage assessment. However, remote sensing images are inherently affected by illumination variations and seasonal changes, which introduce complex pseudochange noise. In addition, traditional hierarchical network architectures struggle to effectively balance multiscale structural boundaries and global texture consistency. To address these challenges, this article proposes a memory-sustained structure-texture representation network (MSST-Net). The network consists of three key components. Hierarchical group-grid coordination module is designed within the hierarchical backbone to suppress shallow feature noise, promote cross-scale collaboration among hierarchical features, and align spatial discrepancies. Bitemporal memory-augmented module is introduced, which integrates learnable memory matrices into the cross-attention mechanism to establish stable semantic correspondence between bi-temporal images. Structure-texture fusion module is further designed based on a structure–texture disentanglement strategy to separately refine the macroscopic structural information and fine-grained texture details of buildings, thereby accomplishing the change detection task. MSST-Net achieves F1 of 92.08%, 94.84%, and 89.39% on three public datasets LEVIR-CD, WHU-CD, and GZ-CD, respectively, demonstrating the effectiveness of the proposed network and the rationality of its architectural design.