University of Oulu

Huynh L., Nguyen-Ha P., Matas J., Rahtu E., Heikkilä J. (2020) Guiding Monocular Depth Estimation Using Depth-Attention Volume. In: Vedaldi A., Bischof H., Brox T., Frahm JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol 12371. Springer, Cham.

Guiding monocular depth estimation using depth-attention volume

Saved in:
Author: Huynh, Lam1; Nguyen-Ha, Phong1; Matas, Jiri2;
Organizations: 1Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2Center for Machine Perception, Czech Technical University, Czech Republic
3Computer Vision Group, Tampere University, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 7.2 MB)
Persistent link:
Language: English
Published: Newswood, 2020
Publish Date: 2021-01-07


Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV). Experiments on two popular indoor datasets, namely NYU-Depth-v2 and ScanNet, show that our method achieves state-of-the-art depth estimation results while using only a fraction of the number of parameters needed by the competing methods. Code is available at:

see all

Series: Lecture notes in engineering and computer science
ISSN: 2078-0958
ISSN-E: 2078-0966
ISSN-L: 2078-0958
ISBN: 978-3-030-58574-7
ISBN Print: 978-3-030-58573-0
Pages: 581 - 597
DOI: 10.1007/978-3-030-58574-7_35
Host publication: Computer Vision – ECCV 2020 - 16th European Conference, 2020, Proceedings
Host publication editor: Vedaldi, Andrea
Bischof, Horst
Brox, Thomas
Frahm, Jan-Michael
Conference: European Conference on Computer Vision
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Copyright information: © Springer Nature Switzerland AG 2020. This is a post-peer-review, pre-copyedit version of an article published in Computer Vision – ECCV 2020 - 16th European Conference, 2020, Proceedings. The final authenticated version is available online at: