Publications

Detailed Information

MIRROR: Towards Generalizable On-Device Video Virtual Try-On for Mobile Shopping

DC Field Value Language
dc.contributor.authorKang, Dong-Sig-
dc.contributor.authorBaek, Eunsu-
dc.contributor.authorSon, Sungwook-
dc.contributor.authorLee, Youngki-
dc.contributor.authorGong, Taesik-
dc.contributor.authorKim, Hyung-Sin-
dc.date.accessioned2024-05-14T08:05:58Z-
dc.date.available2024-05-14T08:05:58Z-
dc.date.created2024-02-01-
dc.date.issued2023-12-
dc.identifier.citationProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol.7 No.4, p. 163-
dc.identifier.issn2474-9567-
dc.identifier.urihttps://hdl.handle.net/10371/202131-
dc.description.abstractWe present MIRROR, an on-device video virtual try-on (VTO) system that provides realistic, private, and rapid experiences in mobile clothes shopping. Despite recent advancements in generative adversarial networks (GANs) for VTO, designing MIRROR involves two challenges: (1) data discrepancy due to restricted training data that miss various poses, body sizes, and backgrounds and (2) local computation overhead that uses up 24% of battery for converting only a single video. To alleviate the problems, we propose a generalizable VTO GAN that not only discerns intricate human body semantics but also captures domain-invariant features without requiring additional training data. In addition, we craft lightweight, reliable clothes/pose-tracking that generates refined pixel-wise warping flow without neural-net computation. As a holistic system, MIRROR integrates the new VTO GAN and tracking method with meticulous pre/post-processing, operating in two distinct phases (on/offline). Our results on Android smartphones and real-world user videos show that compared to a cutting-edge VTO GAN, MIRROR achieves 6.5× better accuracy with 20.1× faster video conversion and 16.9× less energy consumption.-
dc.language영어-
dc.publisherAssociation for Computing Machinery (ACM)-
dc.titleMIRROR: Towards Generalizable On-Device Video Virtual Try-On for Mobile Shopping-
dc.typeArticle-
dc.identifier.doi10.1145/3631420-
dc.citation.journaltitleProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies-
dc.identifier.wosid001168287200018-
dc.identifier.scopusid2-s2.0-85182605561-
dc.citation.number4-
dc.citation.startpage163-
dc.citation.volume7-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorLee, Youngki-
dc.contributor.affiliatedAuthorKim, Hyung-Sin-
dc.type.docTypeArticle-
dc.description.journalClass1-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • Graduate School of Data Science
Research Area Distributed machine learning, Edge, Mobile AI

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share