Cookies

We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.


Durham Research Online
You are in:

Veritatem dies aperit - temporally consistent depth prediction enabled by a multi-task geometric and semantic scene understanding approach.

Atapour-Abarghouei, A. and Breckon, T.P. (2019) 'Veritatem dies aperit - temporally consistent depth prediction enabled by a multi-task geometric and semantic scene understanding approach.', IEEE/CVF Conference on Computer Vision and Pattern Recognition Long Beach, California, USA, 16-20 June 2019.


Item Type:Conference item (Paper)
Keywords:Monocular depth, Generative adversarial network, GAN, Depth map, Disparity, Depth from single image, Multiple task learning, Semantic segmantation, Temporal consistency
Full text:(AM) Accepted Manuscript
Download PDF
(2931Kb)
Status:Peer-reviewed
Publisher Web site:http://cvpr2019.thecvf.com/
Supplementary material:https://vimeo.com/325161805
Date accepted:25 February 2019
Date deposited:26 March 2019
Date of first online publication:June 2019
Date first made open access:13 November 2019

Save or Share this output

Export:
Export
Look up in GoogleScholar