Recent Progress in Shape from Polarization

Abstract

Photometric cues play an important role in recovering per-pixel 3D information from images. Shape from shading and photometric stereo are popular photometric 3D reconstruction approaches, which rely on inversely analyzing an image formation model of the surface normal, reflectance, and lighting. Similarly, shape from polarization explores radiance variation under different polarizer angles to estimate the surface normal, which does not require an active light source and has less restricted assumptions on reflectance and lighting. This chapter reviews basic principles of shape from polarization and its image formation model for surfaces of different reflection properties. We then survey recent progress in shape from polarization combined with different auxiliary information such as geometric cues, spectral cues, photometric cues, and deep learning, and further introduce how polarization imaging benefits other vision tasks in addition to shape recovery.