Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild (Extended Abstract)
-
- Shangzhe Wu
- University of Oxford
-
- Christian Rupprecht
- University of Oxford
-
- Andrea Vedaldi
- University of Oxford
説明
<jats:p>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.</jats:p>
収録刊行物
-
- Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
-
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 4854-4858, 2021-08
International Joint Conferences on Artificial Intelligence Organization