CRD-Net: Frequency-Adaptive Feature Injection and Change Decoupling for Building Damage Assessment

Building damage assessment is crucial for post-disaster re-lief and reconstruction. However, current assessment methods utilizinghigh-resolution remote sensing imagery struggle to represent x001Cne-graineddetails, as subtle damage signals are easily overwhelmed by complexbackgrounds. To address this, we propose a Frequency-Adaptive FeatureInjection and Change Decoupling framework. For feature encoding, wex001Cne-tune a DINOv3 encoder with a frequency-adaptive guidance strat-egy to acutely capture subtle damage. For decoding, we introduce theChange Representation Decoupling and Discriminative Decoder (CRD2 ).CRD2 leverages the Mamba model to ex001Eciently fuse multi-scale fea-tures for spatiotemporal dynamics. To prevent minor damage from be-ing submerged, it utilizes orthogonal subspace projection to isolate purechange features and applies class-prototype contrastive learning for pre-cise damage-level identix001Ccation. Extensive experiments show our CRD-Net achieves state-of-the-art Joint F1 scores on the xBD (81.26%) andEBD (81.88%) datasets.