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.
Cite
Text
Chen et al. "Learning Single-Image Depth from Videos Using Quality Assessment Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00575Markdown
[Chen et al. "Learning Single-Image Depth from Videos Using Quality Assessment Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/chen2019cvpr-learning-a/) doi:10.1109/CVPR.2019.00575BibTeX
@inproceedings{chen2019cvpr-learning-a,
title = {{Learning Single-Image Depth from Videos Using Quality Assessment Networks}},
author = {Chen, Weifeng and Qian, Shengyi and Deng, Jia},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00575},
url = {https://mlanthology.org/cvpr/2019/chen2019cvpr-learning-a/}
}