Edinburgh Research Explorer

Digging Into Self-Supervised Monocular Depth Estimation

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

Related Edinburgh Organisations

Open Access permissions

Open

Original languageEnglish
Title of host publicationThe IEEE International Conference on Computer Vision (ICCV)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages11
Publication statusAccepted/In press - 22 Jul 2019
EventInternational Conference on Computer Vision 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019
http://iccv2019.thecvf.com/

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