DESC: Domain Adaptation for Depth Estimation via semantic consistency
File(s)
Published version
Author(s)
Lopez-Rodriguez, Adrian
Mikolajczyk, Krystian
Type
Journal Article
Abstract
Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be available. Instead, in this paper, we propose a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotated target dataset. We bridge the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain. We enforce consistency between the main model and a second model trained with semantic segmentation and edge maps, and introduce priors in the form of instance heights. Our approach is evaluated on standard domain adaptation benchmarks for monocular depth estimation and show consistent improvement upon the state-of-the-art. Code available at https://github.com/alopezgit/DESC.
Date Issued
2023-03-01
Date Acceptance
2022-11-07
Citation
International Journal of Computer Vision, 2023, 131 (3), pp.752-771
ISSN
0920-5691
Publisher
Springer Science and Business Media LLC
Start Page
752
End Page
771
Journal / Book Title
International Journal of Computer Vision
Volume
131
Issue
3
Copyright Statement
©TheAuthor(s) 2022 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
License URL
Publication Status
Published
Date Publish Online
2022-12-15