Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach

Atapour-Abarghouei, A.; Breckon, T.P.

Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach Thumbnail

Authors

Dr Amir Atapour-Abarghouei amir.atapour-abarghouei@durham.ac.uk
Assistant Professor

Professor Toby Breckon toby.breckon@durham.ac.uk
Professor

Citation

Atapour-Abarghouei, A., & Breckon, T. (2019). Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach. In IEEE Conference on Computer Vision and Pattern Recognition, Deep Vision Long Beach, CA, USA, 16-20 June 2019

Conference Name	IEEE/CVF Conference on Computer Vision and Pattern Recognition
Conference Location	Long Beach, California, USA
Start Date	Jun 16, 2019
End Date	Jun 20, 2019
Acceptance Date	Feb 25, 2019
Publication Date	Jun 1, 2019
Deposit Date	Mar 25, 2019
Publicly Available Date	Nov 13, 2019
Publisher	Institute of Electrical and Electronics Engineers
Book Title	IEEE Conference on Computer Vision and Pattern Recognition, Deep Vision Long Beach, CA, USA, 16-20 June 2019
Keywords	Monocular depth, Generative adversarial network, GAN, Depth map, Disparity, Depth from single image, Multiple task learning, Semantic segmantation, Temporal consistency
Public URL	https://durham-repository.worktribe.com/output/1142446
Publisher URL	http://cvpr2019.thecvf.com/