Unsupervised Learning of 3D Structure from Images

07/03/2016 ∙ by Danilo Jimenez Rezende, et al. ∙ 0

A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods on several datasets, including ShapeNet [2], and establish the first benchmarks in the literature. We also show how these models and their inference networks can be trained end-to-end from 2D images. This demonstrates for the first time the feasibility of learning to infer 3D representations of the world in a purely unsupervised manner.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 7

page 8

page 13

page 14

page 15

page 16

Code Repositories

Ziv--under-dev

Computer game that visualizes musical components and lyrics of user-chosen song. Unreal Engine 3, Tensorflow, OpenCV, Python


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.