Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
 
conference paper

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

Roy, Soumava Kumar  
•
Citraro, Leonardo  
•
Honari, Sina  
Show more
September 12, 2022
2022 International Conference On 3D Vision, 3Dv
10th International Conference on 3D Vision 2022 (3DV)

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted towards semi- and weakly-supervised learning. Generating an effective form of supervision with little annotations still poses major challenge in crowded scenes. In this paper we propose to impose multi-view geometrical constraints by means of a weighted differentiable triangulation and use it as a form of self-supervision when no labels are available. We therefore train a 2D pose estimator in such a way that its predictions correspond to the re-projection of the triangulated 3D pose and train an auxiliary network on them to produce the final 3D poses. We complement the triangulation with a weighting mechanism that alleviates the impact of noisy predictions caused by self-occlusion or occlusion from other subjects. We demonstrate the effectiveness of our semi-supervised approach on Human3.6M and MPI-INF-3DHP datasets, as well as on a new multi-view multi-person dataset that features occlusion.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

3dv-144-camera-ready.pdf

Type

Postprint

Version

http://purl.org/coar/version/c_ab4af688f83e57aa

Access type

openaccess

License Condition

copyright

Size

2.66 MB

Format

Adobe PDF

Checksum (MD5)

1d58839689099f3fce19d4c7253e1470

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés