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

11/25/2019
by   Shangzhe Wu, et al.
26

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.

READ FULL TEXT

page 1

page 7

page 8

page 13

page 14

page 15

page 16

page 17

06/04/2019

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

We show that generative models can be used to capture visual geometry co...
06/09/2017

Unsupervised learning of object frames by dense equivariant image labelling

One of the key challenges of visual perception is to extract abstract mo...
08/02/2020

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...
04/08/2021

De-rendering the World's Revolutionary Artefacts

Recent works have shown exciting results in unsupervised image de-render...
04/03/2020

Self-Supervised Viewpoint Learning From Image Collections

Training deep neural networks to estimate the viewpoint of objects requi...
09/22/2016

Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation

Many objects, especially these made by humans, are symmetric, e.g. cars ...

Code Repositories

unsup3d

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


view repo

unsup3D_pytorch3d

(CVPR'20 Best Paper) Unsup3D SoftRas


view repo

CVPR-2020

CVPR 2020论文相关分享


view repo

Please sign up or login with your details

Forgot password? Click here to reset