2019/03/25 by Yunhao Ba, Alex Ross Gilbert, Ba, Yunhao +15 · 1 citation
Computer Science · Physics and Astronomy · #Color Science and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques #Machine Learning (cs.LG) #Optical measurement and interference techniques
paper · pdf · doi:10.48550/arxiv.1903.10210
openalex publication_date 2019/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper makes a first attempt to bring the Shape from Polarization (SfP) problem to the realm of deep learning. The previous state-of-the-art methods for SfP have been purely physics-based. We see value in these principled models, and blend these physical models as priors into a neural network architecture. This proposed approach achieves results that exceed the previous state-of-the-art on a challenging dataset we introduce. This dataset consists of polarization images taken over a range of object textures, paints, and lighting conditions. We report that our proposed method achieves the lowest test error on each tested condition in our dataset, showing the value of blending data-driven and physics-driven approaches.