Structure-Aware Consistency Priors for Shape from Polarization in Complex Media
For researchers in computer vision and polarization imaging, this work provides a generalizable solution for high-precision geometric perception in complex media, though it is domain-specific to ice.
The paper tackles surface normal recovery from single-view polarization images in complex media like ice, proposing a structure-aware prior and a dual-branch network (IceSfP) that outperforms existing methods, achieving a MAE of 16.01°, 2.74° lower than the second-best.
Recovering surface normals from single view polarization images in complex media remains challenging. This paper focuses on ice as a representative complex medium, where intricate light matter interactions lead to a nonlinear mapping between polarization observations and surface normals. To address this, a structure-aware polarization prior based on autocorrelation functions is proposed to capture the local spatial consistency of AoLP. Building on this, a dual-branch network (IceSfP) is designed to integrate raw polarization features with priors via cross modal attention and multi-scale feature fusion, enabling accurate surface normal estimation under complex media conditions. To evaluate the method, the first real-world ice SfP dataset is constructed. Experimental results show that the method outperforms existing approaches across all metrics, achieving a MAE of 16.01 deg, which is 2.74 deg lower than the second-best method. The framework provides a generalizable solution for high-precision geometric perception in complex media.