@inproceedings{7011ca0625fb4543a6d7ab01f6099deb,
title = "Monocular Depth Estimation Via Deep Structured Models with Ordinal Constraints",
abstract = "User interaction provides useful information for solving challenging computer vision problems in practice. In this paper, we show that a very limited number of user clicks could greatly boost monocular depth estimation performance and overcome monocular ambiguities. We formulate this task as a deep structured model, in which the structured pixel-wise depth estimation has ordinal constraints introduced by user clicks. We show that the inference of the proposed model could be efficiently solved through a feed-forward network. We demonstrate the effectiveness of the proposed model on NYU Depth V2 and Stanford 2D-3D datasets. On both datasets, we achieve state-of-the-art performance when encoding user interaction into our deep models.",
keywords = "Deep structured models, Monocular depth estimation, Ordinal constraints",
author = "Daniel Ron and Kun Duan and Chongyang Ma and Ning Xu and Shenlong Wang and Sumant Hanumante and Dhritiman Sagar",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 6th International Conference on 3D Vision, 3DV 2018 ; Conference date: 05-09-2018 Through 08-09-2018",
year = "2018",
month = oct,
day = "12",
doi = "10.1109/3DV.2018.00071",
language = "English (US)",
series = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "570--577",
booktitle = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
address = "United States",
}