UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Godard, C; Mac Aodha, O; Brostow, GJ; (2017) Unsupervised Monocular Depth Estimation with Left-Right Consistency. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 6602-6611). IEEE: Honolulu, HI, USA. Green open access

[thumbnail of 1609.03677[1].pdf]
Preview
Text
1609.03677[1].pdf - Published Version

Download (7MB) | Preview

Abstract

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality depth data in a range of environments is a challenging problem. In this paper, we innovate beyond existing approaches, replacing the use of explicit depth data during training with easier-to-obtain binocular stereo footage. We propose a novel training objective that enables our convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data. By exploiting epipolar geometry constraints, we generate disparity images by training our networks with an image reconstruction loss. We show that solving for image reconstruction alone results in poor quality depth images. To overcome this problem, we propose a novel training loss that enforces consistency between the disparities produced relative to both the left and right images, leading to improved performance and robustness compared to existing approaches. Our method produces state of the art results for monocular depth estimation on the KITTI driving dataset, even outperforming supervised methods that have been trained with ground truth depth.

Type: Proceedings paper
Title: Unsupervised Monocular Depth Estimation with Left-Right Consistency
Event: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Location: Honolulu, Hawaii, USA
Dates: 22 July 2017 - 25 July 2017
ISBN-13: 978-1-5386-0457-1
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2017.699
Publisher version: http://dx.doi.org/10.1109/CVPR.2017.699
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Estimation, Training, Image reconstruction, Cameras, Predictive models, Neural networks, Lighting
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10039220
Downloads since deposit
259Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item