Learning single-image depth from videos using quality assessment networks

Weifeng Chen, Shengyi Qian, Jia Deng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

42 Scopus citations

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.
Original languageEnglish (US)
Title of host publication2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE
Pages5597-5606
Number of pages10
ISBN (Print)9781728132938
DOIs
StatePublished - Jan 9 2020
Externally publishedYes

Fingerprint

Dive into the research topics of 'Learning single-image depth from videos using quality assessment networks'. Together they form a unique fingerprint.

Cite this