@inproceedings{66a872c5fa4046ee8c666831f425a709,
title = "Learning single-image depth from videos using quality assessment networks",
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.",
keywords = "3D from Single Image, Datasets and Evaluation",
author = "Weifeng Chen and Shengyi Qian and Jia Deng",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 ; Conference date: 16-06-2019 Through 20-06-2019",
year = "2019",
month = jun,
doi = "10.1109/CVPR.2019.00575",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "5597--5606",
booktitle = "Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019",
address = "United States",
}