HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision

Xiaokun Wu; Daniel Finnegan; Eamonn O'Neill; Yongliang Yang

doi:10.1007/978-3-030-01270-0_15

HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision

Xiaokun Wu, Daniel Finnegan, Eamonn O'Neill, Yongliang Yang

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

4 Citations (SciVal)

89 Downloads (Pure)

Abstract

This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision. By leveraging the advantage of predicting heat maps of hand joints in detection-based methods, we propose to use dense feature maps through intermediate supervision in a regression-based framework that is not limited to the resolution of the heat map. Our dense feature maps are delicately designed to encode the hand geometry and the spatial relation between local joint and global hand. The proposed framework significantly improves the state-of-the-art in both 2D and 3D on the recent benchmark datasets.

Original language	English
Title of host publication	Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings
Subtitle of host publication	Computer Vision – ECCV 2018
Editors	Vittorio Ferrari, Martial Hebert, Christian Sminchisescu, Yair Weiss
Publisher	Springer
Pages	246-262
Number of pages	17
ISBN (Electronic)	978-3-030-01270-0
ISBN (Print)	978-3-030-01269-4
DOIs	https://doi.org/10.1007/978-3-030-01270-0_15
Publication status	Published - 2018
Event	15th European Conference on Computer Vision - Munich, Germany Duration: 10 Sept 2018 → 13 Sept 2018

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	11220

Name	Image Processing, Computer Vision, Pattern Recognition, and Graphics
Volume	11220

Conference

Conference	15th European Conference on Computer Vision
Country/Territory	Germany
City	Munich
Period	10/09/18 → 13/09/18

Keywords

Dense guidance map
Hand pose estimation
Intermediate supervision

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-030-01270-0_15

handMap_eccv18.PDF
This is a post-peer-review, pre-copyedit version of an conference article published in ECCV 2018: Computer Vision. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-01270-0_15.
Accepted author manuscript, 3.05 MB

Cite this

Wu, X., Finnegan, D., O'Neill, E., & Yang, Y. (2018). HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Eds.), Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings: Computer Vision – ECCV 2018 (pp. 246-262). ( Lecture Notes in Computer Science; Vol. 11220), (Image Processing, Computer Vision, Pattern Recognition, and Graphics; Vol. 11220). Springer. https://doi.org/10.1007/978-3-030-01270-0_15

HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision. / Wu, Xiaokun; Finnegan, Daniel; O'Neill, Eamonn et al.
Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings: Computer Vision – ECCV 2018. ed. / Vittorio Ferrari; Martial Hebert; Christian Sminchisescu; Yair Weiss. Springer, 2018. p. 246-262 ( Lecture Notes in Computer Science; Vol. 11220), (Image Processing, Computer Vision, Pattern Recognition, and Graphics; Vol. 11220).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Wu, X, Finnegan, D, O'Neill, E & Yang, Y 2018, HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision. in V Ferrari, M Hebert, C Sminchisescu & Y Weiss (eds), Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings: Computer Vision – ECCV 2018. Lecture Notes in Computer Science, vol. 11220, Image Processing, Computer Vision, Pattern Recognition, and Graphics, vol. 11220, Springer, pp. 246-262, 15th European Conference on Computer Vision, Munich, Germany, 10/09/18. https://doi.org/10.1007/978-3-030-01270-0_15

Wu X, Finnegan D, O'Neill E , Yang Y. HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision. In Ferrari V, Hebert M, Sminchisescu C, Weiss Y, editors, Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings: Computer Vision – ECCV 2018. Springer. 2018. p. 246-262. ( Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics). Epub 2018 Oct 6. doi: 10.1007/978-3-030-01270-0_15

Wu, Xiaokun ; Finnegan, Daniel ; O'Neill, Eamonn et al. / HandMap : Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision. Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings: Computer Vision – ECCV 2018. editor / Vittorio Ferrari ; Martial Hebert ; Christian Sminchisescu ; Yair Weiss. Springer, 2018. pp. 246-262 ( Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics).

@inproceedings{20f96b5cd7f34d60b4bdbbbce1e85aa3,

title = "HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision",

abstract = "This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision. By leveraging the advantage of predicting heat maps of hand joints in detection-based methods, we propose to use dense feature maps through intermediate supervision in a regression-based framework that is not limited to the resolution of the heat map. Our dense feature maps are delicately designed to encode the hand geometry and the spatial relation between local joint and global hand. The proposed framework significantly improves the state-of-the-art in both 2D and 3D on the recent benchmark datasets.",

keywords = "Dense guidance map, Hand pose estimation, Intermediate supervision",

author = "Xiaokun Wu and Daniel Finnegan and Eamonn O'Neill and Yongliang Yang",

year = "2018",

doi = "10.1007/978-3-030-01270-0_15",

language = "English",

isbn = "978-3-030-01269-4",

series = " Lecture Notes in Computer Science",

publisher = "Springer",

pages = "246--262",

editor = "Vittorio Ferrari and Martial Hebert and Christian Sminchisescu and Yair Weiss",

booktitle = "Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings",

note = "15th European Conference on Computer Vision ; Conference date: 10-09-2018 Through 13-09-2018",

}

TY - GEN

T1 - HandMap

T2 - 15th European Conference on Computer Vision

AU - Wu, Xiaokun

AU - Finnegan, Daniel

AU - O'Neill, Eamonn

AU - Yang, Yongliang

PY - 2018

Y1 - 2018

N2 - This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision. By leveraging the advantage of predicting heat maps of hand joints in detection-based methods, we propose to use dense feature maps through intermediate supervision in a regression-based framework that is not limited to the resolution of the heat map. Our dense feature maps are delicately designed to encode the hand geometry and the spatial relation between local joint and global hand. The proposed framework significantly improves the state-of-the-art in both 2D and 3D on the recent benchmark datasets.

AB - This work presents a novel hand pose estimation framework via intermediate dense guidance map supervision. By leveraging the advantage of predicting heat maps of hand joints in detection-based methods, we propose to use dense feature maps through intermediate supervision in a regression-based framework that is not limited to the resolution of the heat map. Our dense feature maps are delicately designed to encode the hand geometry and the spatial relation between local joint and global hand. The proposed framework significantly improves the state-of-the-art in both 2D and 3D on the recent benchmark datasets.

KW - Dense guidance map

KW - Hand pose estimation

KW - Intermediate supervision

UR - http://www.scopus.com/inward/record.url?scp=85055105221&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01270-0_15

DO - 10.1007/978-3-030-01270-0_15

M3 - Chapter in a published conference proceeding

SN - 978-3-030-01269-4

T3 - Lecture Notes in Computer Science

SP - 246

EP - 262

BT - Computer Vision – ECCV 2018 - 15th European Conference, 2018, Proceedings

A2 - Ferrari, Vittorio

A2 - Hebert, Martial

A2 - Sminchisescu, Christian

A2 - Weiss, Yair

PB - Springer

Y2 - 10 September 2018 through 13 September 2018

ER -

HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

Cite this

HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map Supervision

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

Cite this