Learning to Predict Keypoints and Structure of Articulated Objects without Supervision

Anciukevicius, T., Henderson, P. and Bilen, H. (2022) Learning to Predict Keypoints and Structure of Articulated Objects without Supervision. In: 26th International Conference on Pattern Recognition (ICPR 2022), Montréal, Québec, Canada, 21-25 August 2022, pp. 3383-3390. ISBN 9781665490627 (doi: 10.1109/ICPR56361.2022.9956688)

[img] Text
277024.pdf - Accepted Version

5MB

Abstract

Reasoning about the structure and motion of novel object classes is a core ability in human cognition, crucial for manipulating objects and predicting their possible motion. We present a method that learns to infer the skeleton structure of a novel articulated object from a single image, in terms of joints and rigid links connecting them. The model learns without supervision from a dataset of objects having diverse structures, in different poses and states of articulation. To achieve this, it is trained to explain the differences between pairs of images in terms of a latent skeleton that defines how to transform one into the other. Experiments on several datasets show that our model predicts joint locations significantly more accurately than prior works on unsupervised keypoint discovery; moreover, unlike existing methods, it can predict varying numbers of joints depending on the observed object. It also successfully predicts the connections between joints, even for structures not seen during training.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Henderson, Dr Paul
Authors: Anciukevicius, T., Henderson, P., and Bilen, H.
College/School:College of Science and Engineering > School of Computing Science
ISSN:2831-7475
ISBN:9781665490627
Copyright Holders:Copyright © 2022 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record