BROWSE

Related Researcher

Author's Photo

Baek, Seungryul
Research Interests

ITEM VIEW & DOWNLOAD

End-to-end detection and pose estimation of two interacting hands

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
End-to-end detection and pose estimation of two interacting hands
Author
Kim, Dong UkKim, Kwang InBaek, Seungryul
Issue Date
2021-10-11
Publisher
IEEE
Citation
IEEE International Conference on Computer Vision, pp.11189 - 11198
Abstract
Three dimensional hand pose estimation has reached a level of maturity, enabling real-world applications for single-hand cases. However, accurate estimation of the pose of two closely interacting hands still remains a challenge as in this case, one hand often occludes the other. We present a new algorithm that accurately estimates hand poses in such a challenging scenario. The crux of our algorithm lies in a framework that jointly trains the estimators of interacting hands, leveraging their interdependence. Further, we employ a GAN-type discriminator of interacting hand pose that helps avoid physically implausible configurations, e.g. intersecting fingers, and exploit the visibility of joints to improve intermediate 2D pose estimation. We incorporate them into a single model that learns to detect hands and estimate their pose based on a unified criterion of pose estimation accuracy. To our knowledge, this is the first attempt to build an end-to-end network that detects and estimates the pose of two closely interacting hands (as well as single hands). In the experiments with three datasets representing challenging real-world scenarios, our algorithm demonstrated significant and consistent performance improvements over state-of-the-arts.
URI
https://scholarworks.unist.ac.kr/handle/201301/54602
URL
https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_End-to-End_Detection_and_Pose_Estimation_of_Two_Interacting_Hands_ICCV_2021_paper.pdf
DOI
10.1109/ICCV48922.2021.01100
Appears in Collections:
AI_Conference Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU