Godard, Clément and Mac Aodha, Oisin and Firman, Michael and Brostow, Gabriel (2019) Digging Into Self-Supervised Monocular Depth Estimation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE , Piscataway, NJ, pp. 3827-3837. ISBN 9781728148038. https://resolver.caltech.edu/CaltechAUTHORS:20200306-092558467
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200306-092558467
Abstract
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.
Item Type: | Book Section | ||||||
---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||
ORCID: |
| ||||||
Additional Information: | © 2019 IEEE. Thanks to the authors who shared their results, and Peter Hedman, Daniyar Turmukhambetov, and Aron Monszpart for their helpful discussions. | ||||||
DOI: | 10.1109/ICCV.2019.00393 | ||||||
Record Number: | CaltechAUTHORS:20200306-092558467 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20200306-092558467 | ||||||
Official Citation: | C. Godard, O. M. Aodha, M. Firman and G. Brostow, "Digging Into Self-Supervised Monocular Depth Estimation," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 3827-3837. doi: 10.1109/ICCV.2019.00393 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 101736 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | Tony Diaz | ||||||
Deposited On: | 06 Mar 2020 17:43 | ||||||
Last Modified: | 16 Nov 2021 18:05 |
Repository Staff Only: item control page