What Do Single-View 3D Reconstruction Networks Learn?

Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output s...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 3400 - 3409
Main Authors:	Tatarchenko, Maxim, Richter, Stephan R., Ranftl, Rene, Li, Zhuwen, Koltun, Vladlen, Brox, Thomas
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.06.2019
Subjects:	3D from Single Image Cognition Computer vision Convolutional neural networks Coordinate measuring machines Deep Learning Image classification Image reconstruction Pattern recognition Three-dimensional displays
ISSN:	1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output space. In this work, we set up two alternative approaches that perform image classification and retrieval respectively. These simple baselines yield better results than state-of-the-art methods, both qualitatively and quantitatively. We show that encoder-decoder methods are statistically indistinguishable from these baselines, thus indicating that the current state of the art in single-view object reconstruction does not actually perform reconstruction but image classification. We identify aspects of popular experimental procedures that elicit this behavior and discuss ways to improve the current state of research.
ISSN:	1063-6919
DOI:	10.1109/CVPR.2019.00352