Learning Single-Image Depth From Videos Using Quality Assessment Networks

Weifeng Chen, Shengyi Qian, Jia Deng; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5604-5613

Abstract


Depth estimation from a single image in the wild remains a challenging problem. One main obstacle is the lack of high-quality training data for images in the wild. In this paper we propose a method to automatically generate such data through Structure-from-Motion (SfM) on Internet videos. The core of this method is a Quality Assessment Network that identifies high-quality reconstructions obtained from SfM. Using this method, we collect single-view depth training data from a large number of YouTube videos and construct a new dataset called YouTube3D. Experiments show that YouTube3D is useful in training depth estimation networks and advances the state of the art of single-view depth estimation in the wild.

Related Material


[pdf]
[bibtex]
@InProceedings{Chen_2019_CVPR,
author = {Chen, Weifeng and Qian, Shengyi and Deng, Jia},
title = {Learning Single-Image Depth From Videos Using Quality Assessment Networks},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}