SAS-Net: Scene-Appearance Separation Network for Robust Spatiotemporal Registration in Bidirectional Photoacoustic Microscopy

High-speed optical-resolution photoacoustic microscopy (OR-PAM) with bidirectional scanning enables rapid functional brain imaging but introduces severe spatiotemporalmisalignment from coupled scan-direction-dependent domain shift and geometric distortion. Conventional registration methods rely on brightness constancy, an assumptionviolated under bidirectional scanning, leading to unreliable alignment. A unified scene-appearance separation framework is proposed to jointly address domain shift andspatial misalignment. The proposed architecture separates domain-invariant scene content from domain-specific appearance characteristics, enabling cross-domainreconstruction with geometric preservation. A scene consistency loss promotes geometric correspondence in the latent space, linking domain shift correction with spatialregistration within a single framework. For in vivo mouse brain vasculature imaging, the proposed method achieves normalized cross-correlation (NCC) of 0.961 andstructural similarity index (SSIM) of 0.894, substantially outperforming conventional methods. Ablation studies demonstrate that domain alignment loss is critical,with its removal causing 82% NCC reduction (0.961 to 0.175), while scene consistency and cycle consistency losses provide complementary regularization for optimalperformance. The method achieves 11.2 ms inference time per frame (86 fps), substantially exceeding typical OR-PAM acquisition rates and enabling real-time processing.These results suggest that the proposed framework enables robust high-speed bidirectional OR-PAM for reliable quantitative and longitudinal functional imaging. The code will be publicly available atthis https URL