Deep Shape from Polarization
arXiv:1903.10210
Abstract
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Neural Lander: Stable Drone Landing Control using Learned Dynamics
- Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
- Deep Networks with Stochastic Depth
- Low Photon Count Phase Retrieval Using Deep Learning
- Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
- From Shading to Local Shape
- Neural Inverse Rendering for General Reflectance Photometric Stereo
- Physics-Based Generative Adversarial Models for Image Restoration and Beyond
- Flash Photography for Data-Driven Hidden Scene Recovery
- Inverse Transport Networks
- Reblur2Deblur: Deblurring Videos via Self-Supervised Learning