Indoor Scene Structure Analysis for Single Image Depth Estimation

Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 614-622

Abstract


We tackle the problem of single image depth estimation, which, without additional knowledge, suffers from many ambiguities. Unlike previous approaches that only reason locally, we propose to exploit the global structure of the scene to estimate its depth. To this end, we introduce a hierarchical representation of the scene, which models local depth jointly with mid-level and global scene structures. We formulate single image depth estimation as inference in a graphical model whose edges let us encode the interactions within and across the different layers of our hierarchy. Our method therefore still produces detailed depth estimates, but also leverages higher-level information about the scene. We demonstrate the benefits of our approach over local depth estimation methods on standard indoor datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhuo_2015_CVPR,
author = {Zhuo, Wei and Salzmann, Mathieu and He, Xuming and Liu, Miaomiao},
title = {Indoor Scene Structure Analysis for Single Image Depth Estimation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}