PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion

Zeng, H; Dai, Y; Yu, X; Wang, X; Yang, Y

PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion

Zeng, H Dai, Y Yu, X

Wang, X Yang, Y

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2022, 00, pp. 5580-5589
Issue Date:: 2022-02-28

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 28 Feb 2024

Adobe PDF

Download Accepted versionAdobe PDF (3.89 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zeng, H
dc.contributor.author	Dai, Y
dc.contributor.author	Yu, X https://orcid.org/0000-0002-0269-5649
dc.contributor.author	Wang, X
dc.contributor.author	Yang, Y
dc.date	2021-10-10
dc.date.accessioned	2022-04-11T23:39:29Z
dc.date.available	2022-04-11T23:39:29Z
dc.date.issued	2022-02-28
dc.identifier.citation	2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2022, 00, pp. 5580-5589
dc.identifier.uri	http://hdl.handle.net/10453/156100
dc.description.abstract	We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity pairs of frames than low-rigidity pairs. We propose minimum singular-value ratio to measure the pairwise rigidity. The Pairwise Consistency Loss enforces the reconstruction to be consistent when the estimated shapes and cameras are exchanged between pairs. Our approach achieves state-of-the-art performance on CMU MOCAP and PASCAL3D+ dataset.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2021 IEEE/CVF International Conference on Computer Vision (ICCV)
dc.relation.ispartof	2021 IEEE/CVF International Conference on Computer Vision
dc.relation.isbasedon	10.1109/iccv48922.2021.00555
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Montreal, QC, Canada
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
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2024-02-28T00:00:00+1000Z
dc.date.updated	2022-04-11T23:39:27Z
pubs.finish-date	2021-10-17
pubs.publication-status	Published
pubs.start-date	2021-10-10
pubs.volume	00

Abstract:

We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity pairs of frames than low-rigidity pairs. We propose minimum singular-value ratio to measure the pairwise rigidity. The Pairwise Consistency Loss enforces the reconstruction to be consistent when the estimated shapes and cameras are exchanged between pairs. Our approach achieves state-of-the-art performance on CMU MOCAP and PASCAL3D+ dataset.

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

http://hdl.handle.net/10453/156100