Deep Learning Methods for Calibrated Photometric Stereo and Beyond

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues,i.e.,modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixelresolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused bynon-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context ofphotometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-basedcalibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methodsfrom different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deeplearning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance ofdeep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on thelimitations of existing models.