Proceedings

Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild (Extended Abstract)

Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 4854-4858.

https://doi.org/10.24963/ijcai.2021/665

Keywords

  • Computer Vision: Computational Photography, Photometry, Shape from X
  • Computer Vision: 2D and 3D Computer Vision

Abstract

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 approximately, 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. Code and demo available at https://github.com/elliottwu/unsup3d.

Shangzhe Wu, Christian Rupprecht, and Andrea Vedaldi. 2021. Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild (Extended Abstract). In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4854–4858. https://doi.org/10.24963/ijcai.2021/665
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards