Work

Learning Single-Image Depth From Videos Using Quality Assessment Networks

Year: 2019
Type: conference-paper
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.
Language: English
Open Access status: green
OpenAlex ID: W2886668163
FWCI: 3.476
Cites: 74
Cited by: 74
Related to: 10