Deep Learning Methods for Calibrated Photometric Stereo and Beyond
It provides a comprehensive analysis for researchers in computer vision, but it is incremental as it reviews existing methods without introducing new techniques.
This paper reviews deep learning methods for calibrated photometric stereo, which tackles the problem of recovering surface normals from images with varying shading cues, particularly for non-Lambertian surfaces, and demonstrates their advanced performance on benchmark datasets.
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-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models.