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

Weakly-supervised mesh-convolutional hand reconstruction in the wild

Kulon, D; Güler, RA; Kokkinos, I; Bronstein, M; Zafeiriou, S; (2020) Weakly-supervised mesh-convolutional hand reconstruction in the wild. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. (pp. pp. 4989-4999). IEEE: Seattle, WA, USA, USA. Green open access

[thumbnail of 2004.01946.pdf]
Preview
Text
2004.01946.pdf - Accepted version

Download (4MB) | Preview

Abstract

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss. We train our network by gathering a large-scale dataset of hand action in YouTube videos and use it as a source of weak supervision. Our weakly-supervised mesh convolutions-based system largely outperforms state-of-the-art methods, even halving the errors on the in the wild benchmark. The dataset and additional resources are available at https://arielai.com/mesh_hands.

Type: Proceedings paper
Title: Weakly-supervised mesh-convolutional hand reconstruction in the wild
Event: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR42600.2020.00504
Publisher version: https://doi.org/10.1109/CVPR42600.2020.00504
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: Three-dimensional displays, Two dimensional displays, Image reconstruction, Pose estimation, Shape, YouTube, Videos
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/10119371
Downloads since deposit
19Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item