Monocular Depth Estimation Via Deep Structured Models with Ordinal Constraints

Daniel Ron, Kun Duan, Chongyang Ma, Ning Xu, Shenlong Wang, Sumant Hanumante, Dhritiman Sagar

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

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.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 International Conference on 3D Vision, 3DV 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages570-577
Number of pages8
ISBN (Electronic)9781538684252
DOIs
StatePublished - Oct 12 2018
Externally publishedYes
Event6th International Conference on 3D Vision, 3DV 2018 - Verona, Italy
Duration: Sep 5 2018Sep 8 2018

Publication series

NameProceedings - 2018 International Conference on 3D Vision, 3DV 2018

Other

Other6th International Conference on 3D Vision, 3DV 2018
Country/TerritoryItaly
CityVerona
Period9/5/189/8/18

Keywords

  • Deep structured models
  • Monocular depth estimation
  • Ordinal constraints

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Monocular Depth Estimation Via Deep Structured Models with Ordinal Constraints'. Together they form a unique fingerprint.

Cite this