File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

김광인

Kim, Kwang In
Machine Learning and Vision Lab.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

S2Contact: Graph-based network for 3D hand-object contact estimation with semi-supervised learning

Author(s)
Tse, Tze Ho EldenZhang, ZhongqunKim, Kwang InLeonardis, AlešZheng, FengChang, Hyung Jin
Issued Date
2022-10-26
URI
https://scholarworks.unist.ac.kr/handle/201301/75300
Fulltext
https://eldentse.github.io/s2contact/
Citation
European Conference on Computer Vision
Abstract
Despite the recent efforts in accurate 3D annotations in hand and object datasets, there still exist gaps in 3D hand and object reconstructions. Existing works leverage contact maps to refine inaccurate hand-object pose estimations and generate grasps given object models. However, they require explicit 3D supervision which is seldom available and therefore, are limited to constrained settings, e.g., where thermal cameras observe residual heat left on manipulated objects. In this paper, we propose a novel semi-supervised framework that allows us to learn contact from monocular images. Specifically, we leverage visual and geometric consistency constraints in large-scale datasets for generating pseudo-labels in semi-supervised learning and propose an efficient graph-based network to infer contact. Our semi-supervised learning framework achieves a favourable improvement over the existing supervised learning methods trained on data with ‘limited’ annotations. Notably, our proposed model is able to achieve superior results with less than half the network parameters and memory access cost when compared with the commonly-used PointNet-based approach. We show benefits from using a contact map that rules hand-object interactions to produce more accurate reconstructions. We further demonstrate that training with pseudo-labels can extend contact map estimations to out-of-domain objects and generalise better across multiple datasets. Project page is available.
Publisher
ECCV 2022

qrcode

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