Monocular Relative Depth Perception With Web Stereo Data Supervision

Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 311-320

Abstract


In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation.

Related Material


[pdf]
[bibtex]
@InProceedings{Xian_2018_CVPR,
author = {Xian, Ke and Shen, Chunhua and Cao, Zhiguo and Lu, Hao and Xiao, Yang and Li, Ruibo and Luo, Zhenbo},
title = {Monocular Relative Depth Perception With Web Stereo Data Supervision},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}