MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views

Zeng, H; Yu, X; Miao, J; Yang, Y

MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views

Zeng, H Yu, X

Miao, J Yang, Y

Permalink

Publisher:: Springer Nature Switzerland
Publication Type:: Chapter
Citation:: Computer Vision – ECCV 2022, 2022, 13662 LNCS, pp. 1-17
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	978-3-031-20086-1_1.pdf	Published version	1.07 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zeng, H
dc.contributor.author	Yu, X https://orcid.org/0000-0002-0269-5649
dc.contributor.author	Miao, J
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date.accessioned	2023-01-27T04:09:34Z
dc.date.available	2023-01-27T04:09:34Z
dc.date.issued	2022-01-01
dc.identifier.citation	Computer Vision – ECCV 2022, 2022, 13662 LNCS, pp. 1-17
dc.identifier.isbn	9783031200854
dc.identifier.uri	http://hdl.handle.net/10453/165528
dc.description.abstract	We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM). MHR-Net aims to find a set of reasonable reconstructions for a 2D view, and it also selects the most likely reconstruction from the set. To deal with the challenging unsupervised generation of non-rigid shapes, we develop a new Deterministic Basis and Stochastic Deformation scheme in MHR-Net. The non-rigid shape is first expressed as the sum of a coarse shape basis and a flexible shape deformation, then multiple hypotheses are generated with uncertainty modeling of the deformation part. MHR-Net is optimized with reprojection loss on the basis and the best hypothesis. Furthermore, we design a new Procrustean Residual Loss, which reduces the rigid rotations between similar shapes and further improves the performance. Experiments show that MHR-Net achieves state-of-the-art reconstruction accuracy on Human3.6M, SURREAL and 300-VW datasets.
dc.language	en
dc.publisher	Springer Nature Switzerland
dc.relation	http://purl.org/au-research/grants/arc/DP200100938
dc.relation.ispartof	Computer Vision – ECCV 2022
dc.relation.isbasedon	10.1007/978-3-031-20086-1_1
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
dc.type	Chapter
utslib.citation.volume	13662 LNCS
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2023-01-27T04:09:32Z
pubs.publication-status	Published
pubs.volume	13662 LNCS

Abstract:

We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM). MHR-Net aims to find a set of reasonable reconstructions for a 2D view, and it also selects the most likely reconstruction from the set. To deal with the challenging unsupervised generation of non-rigid shapes, we develop a new Deterministic Basis and Stochastic Deformation scheme in MHR-Net. The non-rigid shape is first expressed as the sum of a coarse shape basis and a flexible shape deformation, then multiple hypotheses are generated with uncertainty modeling of the deformation part. MHR-Net is optimized with reprojection loss on the basis and the best hypothesis. Furthermore, we design a new Procrustean Residual Loss, which reduces the rigid rotations between similar shapes and further improves the performance. Experiments show that MHR-Net achieves state-of-the-art reconstruction accuracy on Human3.6M, SURREAL and 300-VW datasets.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/165528