Physics-driven semantic scattering structure understanding of aircraft target in SAR images

Synthetic aperture radar (SAR) has become indispensable for target interpretation owing to its all-day and all-weather observation capability. In SAR target interpretation, electromagnetic scattering information provides a physically grounded cue beyond visual texture and has been widely exploited for target interpretation. However, existing methods remain dominated by local scattering center representations. Such unordered and component-agnostic representations are highly unstable for aircraft targets. As a result, physically existing components with weak scattering responses are often missed, resulting in the incomplete reconstructed topology structure. To address this limitation, we establish Semantic Scattering Structure Understanding as a new paradigm for SAR aircraft interpretation. Semantic scattering keypoints are defined to associate local electromagnetic responses with physically meaningful aircraft components, while visibility-aware attributes are introduced to retain weakly observable yet physically existing components. The keypoints are further organized into a stable semantic scattering structure. Building upon this, we propose S 3 U-SAR, a physics-driven framework to localize semantic scattering keypoints and construct the complete representation constrained by multi-dimensional physical priors, including scattering heterogeneity, rigid-body topology, speckle uncertainty. A confidence-gated joint supervision strategy is further introduced to alleviate optimization conflicts. We construct KP-SAR-Aircraft-1.0, the first fine-grained benchmark for semantic scattering structure understanding. Extensive experiments demonstrate that S 3 U-SAR achieves the best performance compared with baselines. Class-disjoint cross-category and cross-dataset evaluations further verify its generalization capability and transferability. Notably, in downstream orientation estimation, the method improves P 1 ° and P 5 ° by 15.0% and 19.1% over the strongest baselines. These results demonstrate the effectiveness of the proposed representation paradigm in advancing SAR target understanding from implicit local response regression toward explicit global structural representation. The trained model and dataset will be available at https://github.com/YYF121/S3U-SAR .