Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to disentangle these components without supervision, we use the fact that many object categories have, at least in principle, a symmetric structure. We show that reasoning about illumination allows us to exploit the underlying object symmetry even if the appearance is not symmetric due to shading. Furthermore, we model objects that are probably, but not certainly, symmetric by predicting a symmetry probability map, learned end-to-end with the other components of the model. Our experiments show that this method can recover very accurately the 3D shape of human faces, cat faces and cars from single-view images, without any supervision or a prior shape model. On benchmarks, we demonstrate superior accuracy compared to another method that uses supervision at the level of 2D image correspondences.

1. Introduction

Understanding the 3D structure of images is key in many computer vision applications. Futhermore, while many deep networks appear to understand images as 2D textures [15], 3D modelling can explain away much of the variability of natural images and potentially improve image understanding in general. Motivated by these facts, we consider the problem of learning 3D models for deformable object categories.