LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping

We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and str...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Choi, Changho, Kim, Minho, Lee, Junhyeok, Song, Hyoung-Kyu, Kim, Younggeun, Kim, Seungryong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Choi, Changho
Kim, Minho
Lee, Junhyeok
Song, Hyoung-Kyu
Kim, Younggeun
Kim, Seungryong
description We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and straightforward. The loss objective consists of only three terms, and can effectively control the face swap results between source and target images. By attaching a pre-trained GAN inversion model independent to the model and using the StyleGAN2 generator, our model produces photorealistic and high-resolution images comparable to other competitive face swap models. We show that our framework is applicable to other generators such as StyleNeRF, paving a way to 3D-aware face swapping and is also compatible with other downstream StyleGAN2 generator tasks. The source code and models can be found at \url{https://github.com/usingcolor/LatentSwap}.
doi_str_mv 10.48550/arxiv.2402.18351
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2402_18351</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2402_18351</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-84de14f56d0fa94744c3b10a8e987e8fe09948c4d6a2084465fd5e20d3c94d173</originalsourceid><addsrcrecordid>eNotj8FOwzAQRH3hgAofwIn9gQQ7Xic2typqKFIQB3qPFnuNLGgSmYrC30NaTiPN04z0hLhRskRrjLyj_J2-ygplVSqrjboU254OPB5ejjTfw3qETYzJp78GzgDaKTA80Tyn8Q26THs-Tvkd4pShI8-wLBd2JS4ifXzy9X-uxK7b7Npt0T8_PLbrvqC6UYXFwAqjqYOM5LBB9PpVSbLsbMM2snQOrcdQUyUtYm1iMFzJoL3DoBq9Erfn25PKMOe0p_wzLErDSUn_Au53RXI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping</title><source>arXiv.org</source><creator>Choi, Changho ; Kim, Minho ; Lee, Junhyeok ; Song, Hyoung-Kyu ; Kim, Younggeun ; Kim, Seungryong</creator><creatorcontrib>Choi, Changho ; Kim, Minho ; Lee, Junhyeok ; Song, Hyoung-Kyu ; Kim, Younggeun ; Kim, Seungryong</creatorcontrib><description>We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and straightforward. The loss objective consists of only three terms, and can effectively control the face swap results between source and target images. By attaching a pre-trained GAN inversion model independent to the model and using the StyleGAN2 generator, our model produces photorealistic and high-resolution images comparable to other competitive face swap models. We show that our framework is applicable to other generators such as StyleNeRF, paving a way to 3D-aware face swapping and is also compatible with other downstream StyleGAN2 generator tasks. The source code and models can be found at \url{https://github.com/usingcolor/LatentSwap}.</description><identifier>DOI: 10.48550/arxiv.2402.18351</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-02</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2402.18351$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2402.18351$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Choi, Changho</creatorcontrib><creatorcontrib>Kim, Minho</creatorcontrib><creatorcontrib>Lee, Junhyeok</creatorcontrib><creatorcontrib>Song, Hyoung-Kyu</creatorcontrib><creatorcontrib>Kim, Younggeun</creatorcontrib><creatorcontrib>Kim, Seungryong</creatorcontrib><title>LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping</title><description>We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and straightforward. The loss objective consists of only three terms, and can effectively control the face swap results between source and target images. By attaching a pre-trained GAN inversion model independent to the model and using the StyleGAN2 generator, our model produces photorealistic and high-resolution images comparable to other competitive face swap models. We show that our framework is applicable to other generators such as StyleNeRF, paving a way to 3D-aware face swapping and is also compatible with other downstream StyleGAN2 generator tasks. The source code and models can be found at \url{https://github.com/usingcolor/LatentSwap}.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FOwzAQRH3hgAofwIn9gQQ7Xic2typqKFIQB3qPFnuNLGgSmYrC30NaTiPN04z0hLhRskRrjLyj_J2-ygplVSqrjboU254OPB5ejjTfw3qETYzJp78GzgDaKTA80Tyn8Q26THs-Tvkd4pShI8-wLBd2JS4ifXzy9X-uxK7b7Npt0T8_PLbrvqC6UYXFwAqjqYOM5LBB9PpVSbLsbMM2snQOrcdQUyUtYm1iMFzJoL3DoBq9Erfn25PKMOe0p_wzLErDSUn_Au53RXI</recordid><startdate>20240228</startdate><enddate>20240228</enddate><creator>Choi, Changho</creator><creator>Kim, Minho</creator><creator>Lee, Junhyeok</creator><creator>Song, Hyoung-Kyu</creator><creator>Kim, Younggeun</creator><creator>Kim, Seungryong</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240228</creationdate><title>LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping</title><author>Choi, Changho ; Kim, Minho ; Lee, Junhyeok ; Song, Hyoung-Kyu ; Kim, Younggeun ; Kim, Seungryong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-84de14f56d0fa94744c3b10a8e987e8fe09948c4d6a2084465fd5e20d3c94d173</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Choi, Changho</creatorcontrib><creatorcontrib>Kim, Minho</creatorcontrib><creatorcontrib>Lee, Junhyeok</creatorcontrib><creatorcontrib>Song, Hyoung-Kyu</creatorcontrib><creatorcontrib>Kim, Younggeun</creatorcontrib><creatorcontrib>Kim, Seungryong</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Choi, Changho</au><au>Kim, Minho</au><au>Lee, Junhyeok</au><au>Song, Hyoung-Kyu</au><au>Kim, Younggeun</au><au>Kim, Seungryong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping</atitle><date>2024-02-28</date><risdate>2024</risdate><abstract>We propose LatentSwap, a simple face swapping framework generating a face swap latent code of a given generator. Utilizing randomly sampled latent codes, our framework is light and does not require datasets besides employing the pre-trained models, with the training procedure also being fast and straightforward. The loss objective consists of only three terms, and can effectively control the face swap results between source and target images. By attaching a pre-trained GAN inversion model independent to the model and using the StyleGAN2 generator, our model produces photorealistic and high-resolution images comparable to other competitive face swap models. We show that our framework is applicable to other generators such as StyleNeRF, paving a way to 3D-aware face swapping and is also compatible with other downstream StyleGAN2 generator tasks. The source code and models can be found at \url{https://github.com/usingcolor/LatentSwap}.</abstract><doi>10.48550/arxiv.2402.18351</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2402.18351
ispartof
issn
language eng
recordid cdi_arxiv_primary_2402_18351
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A28%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=LatentSwap:%20An%20Efficient%20Latent%20Code%20Mapping%20Framework%20for%20Face%20Swapping&rft.au=Choi,%20Changho&rft.date=2024-02-28&rft_id=info:doi/10.48550/arxiv.2402.18351&rft_dat=%3Carxiv_GOX%3E2402_18351%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true