Multi-scale attention guided pose transfer

Roy, P; Bhattacharya, S; Ghosh, S; Pal, U

Multi-scale attention guided pose transfer

Roy, P Bhattacharya, S Ghosh, S Pal, U

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Pattern Recognition, 2023, 137
Issue Date:: 2023-05-01

Closed Access

	Filename	Description	Size
	Multi scale attention guided pose transfer.pdf	Accepted version	6.09 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	Roy, P
dc.contributor.author	Bhattacharya, S
dc.contributor.author	Ghosh, S
dc.contributor.author	Pal, U
dc.date.accessioned	2024-03-15T02:28:45Z
dc.date.available	2024-03-15T02:28:45Z
dc.date.issued	2023-05-01
dc.identifier.citation	Pattern Recognition, 2023, 137
dc.identifier.issn	0031-3203
dc.identifier.issn	1873-5142
dc.identifier.uri	http://hdl.handle.net/10453/176757
dc.description.abstract	Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, pose transfer has been extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. This paper presents an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset. We also show the generality of the proposed network architecture by extending it to multiple application domains, such as semantic reconstruction, virtual try-on and style manipulation.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Pattern Recognition
dc.relation.isbasedon	10.1016/j.patcog.2023.109315
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	4603 Computer vision and multimedia computation
dc.subject.classification	4605 Data management and data science
dc.subject.classification	4611 Machine learning
dc.title	Multi-scale attention guided pose transfer
dc.type	Journal Article
utslib.citation.volume	137
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
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/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-15T02:28:41Z
pubs.publication-status	Published
pubs.volume	137

Abstract:

Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, pose transfer has been extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. This paper presents an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset. We also show the generality of the proposed network architecture by extending it to multiple application domains, such as semantic reconstruction, virtual try-on and style manipulation.

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

http://hdl.handle.net/10453/176757