Unsupervised Learning of Probably Symmetric Deformable 3D Objects
A method to learn 3D deformable object categories from raw single-view images, without external supervision.
3d 3d-objects 3d-reconstruction unsupervised-learning cvpr-2020 pytorch computer-vision article code research paper video demo arxiv:1911.11130

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.

Don't forget to tag @elliottwu in your comment, otherwise they may not be notified.

Authors community post
Share this project
Similar projects
PIFuHD: High-Resolution 3D Human Digitization
This repository contains a pytorch implementation of "Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization".
3D Detection and Domain Adaptation
1st Place Solution for Waymo Open Dataset Challenge
MediaPipe
Simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.
Epipolar Transformers
Differentiable "epipolar transformer", which enables the 2D detector to leverage 3D-aware features to improve 2D pose estimation.