Deep Shape from Polarization
This addresses 3D shape reconstruction from polarization images for computer vision applications, representing an incremental advance by combining existing physics-driven and data-driven methods.
The paper tackles the Shape from Polarization (SfP) problem by introducing a deep learning approach that blends physics-based priors into a neural network, achieving state-of-the-art results with the lowest test error across various object textures, paints, and lighting conditions in a new challenging dataset.
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.