Log In Sign Up

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

by   Shangzhe Wu, et al.

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.


page 1

page 7

page 8

page 13

page 14

page 15

page 16

page 17


Photo-Geometric Autoencoding to Learn 3D Objects from Unlabelled Images

We show that generative models can be used to capture visual geometry co...

Unsupervised learning of object frames by dense equivariant image labelling

One of the key challenges of visual perception is to extract abstract mo...

SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images

We study the problem of symmetry detection of 3D shapes from single-view...

De-rendering the World's Revolutionary Artefacts

Recent works have shown exciting results in unsupervised image de-render...

Self-Supervised Viewpoint Learning From Image Collections

Training deep neural networks to estimate the viewpoint of objects requi...

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images

Recovering the 3D structure of an object from a single image is a challe...

Code Repositories


(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

view repo


(CVPR'20 Best Paper) Unsup3D SoftRas

view repo


CVPR 2020论文相关分享

view repo