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

DensePose: Dense Human Pose Estimation in the Wild.

Güler, RA; Neverova, N; Kokkinos, I; (2018) DensePose: Dense Human Pose Estimation in the Wild. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Proceedings. (pp. pp. 7297-7306). IEEE: Salt Lake City, UT, USA. Green open access

[thumbnail of Guler_DensePose_Dense_Human_CVPR_2018_paper.pdf]
Preview
Text
Guler_DensePose_Dense_Human_CVPR_2018_paper.pdf - Accepted Version

Download (2MB) | Preview

Abstract

In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an inpainting network that can fill in missing ground truth values and report improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter. We further improve accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Supplementary materials, data, code, and videos are provided on the project page http://densepose.org.

Type: Proceedings paper
Title: DensePose: Dense Human Pose Estimation in the Wild.
Event: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2018.00762
Publisher version: https://doi.org/10.1109/CVPR.2018.00762
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.
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/10089419
Downloads since deposit
61Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item