Learning Single-Image Depth From Videos Using Quality Assessment Networks

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

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.