Edinburgh Research Explorer

Digging Into Self-Supervised Monocular Depth Estimation

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

Original languageEnglish
Title of host publication2019 IEEE/CVF International Conference on Computer Vision (ICCV)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages3827-3837
Number of pages11
ISBN (Electronic)978-1-7281-4803-8
ISBN (Print)978-1-7281-4804-5
DOIs
Publication statusPublished - 27 Feb 2020
EventInternational Conference on Computer Vision 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019
http://iccv2019.thecvf.com/

Publication series

Name
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

ConferenceInternational Conference on Computer Vision 2019
Abbreviated titleICCV 2019
CountryKorea, Republic of
CitySeoul
Period27/10/192/11/19
Internet address

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.

Event

International Conference on Computer Vision 2019

27/10/192/11/19

Seoul, Korea, Republic of

Event: Conference

ID: 122451926