3D Keypoint Estimation Using Implicit Representation Learning

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Xiangyu Zhu
  • Dong Du
  • Haibin Huang
  • Chongyang Ma
  • Xiaoguang Han

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article numbere14917
Journal / PublicationComputer Graphics Forum
Volume42
Issue number5
Online published10 Aug 2023
Publication statusPublished - Aug 2023

Abstract

In this paper, we tackle the challenging problem of 3D keypoint estimation of general objects using a novel implicit representation. Previous works have demonstrated promising results for keypoint prediction through direct coordinate regression or heatmap-based inference. However, these methods are commonly studied for specific subjects, such as human bodies and faces, which possess fixed keypoint structures. They also suffer in several practical scenarios where explicit or complete geometry is not given, including images and partial point clouds. Inspired by the recent success of advanced implicit representation in reconstruction tasks, we explore the idea of using an implicit field to represent keypoints. Specifically, our key idea is employing spheres to represent 3D keypoints, thereby enabling the learnability of the corresponding signed distance field. Explicit key-points can be extracted subsequently by our algorithm based on the Hough transform. Quantitative and qualitative evaluations also show the superiority of our representation in terms of prediction accuracy. © 2023 Eurographics - The European Association for Computer Graphics and John Wiley & Sons Ltd.

Research Area(s)

  • CCS Concepts, Shape representations, • Computing methodologies, → Shape analysis

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

3D Keypoint Estimation Using Implicit Representation Learning. / Zhu, Xiangyu; Du, Dong; Huang, Haibin et al.
In: Computer Graphics Forum, Vol. 42, No. 5, e14917, 08.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review