A Foreground-Aware Framework for Local Face Attribute Transfer
In the context of social media, large amounts of headshot photos are taken everyday. Unfortunately, in addition to laborious editing and modification, creating a visually compelling photographic masterpiece for sharing requires advanced professional skills, which are difficult for ordinary Internet...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/5/615 |
| _version_ | 1797533876162134016 |
|---|---|
| author | Yuanbin Fu Jiayi Ma Xiaojie Guo |
| author_facet | Yuanbin Fu Jiayi Ma Xiaojie Guo |
| author_sort | Yuanbin Fu |
| collection | DOAJ |
| description | In the context of social media, large amounts of headshot photos are taken everyday. Unfortunately, in addition to laborious editing and modification, creating a visually compelling photographic masterpiece for sharing requires advanced professional skills, which are difficult for ordinary Internet users. Though there are many algorithms automatically and globally transferring the style from one image to another, they fail to respect the semantics of the scene and are unable to allow users to merely transfer the attributes of one or two face organs in the foreground region leaving the background region unchanged. To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background. Our method involves warping the reference photo to match the shape, pose, location, and expression of the input image. The fusion of the warped reference image and input image is then taken as the initialized image for a neural style transfer algorithm. Our method achieves better performance in terms of inception score (3.81) and Fréchet inception distance (80.31), which is about 10% higher than those of competitors, indicating that our framework is capable of producing high-quality and photorealistic attribute transfer results. Both theoretical findings and experimental results are provided to demonstrate the efficacy of the proposed framework, reveal its superiority over other state-of-the-art alternatives. |
| first_indexed | 2024-03-10T11:21:53Z |
| format | Article |
| id | doaj.art-57646a5aab2c4e799b48773094e29114 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T11:21:53Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-57646a5aab2c4e799b48773094e291142023-11-21T19:56:41ZengMDPI AGEntropy1099-43002021-05-0123561510.3390/e23050615A Foreground-Aware Framework for Local Face Attribute TransferYuanbin Fu0Jiayi Ma1Xiaojie Guo2College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaIn the context of social media, large amounts of headshot photos are taken everyday. Unfortunately, in addition to laborious editing and modification, creating a visually compelling photographic masterpiece for sharing requires advanced professional skills, which are difficult for ordinary Internet users. Though there are many algorithms automatically and globally transferring the style from one image to another, they fail to respect the semantics of the scene and are unable to allow users to merely transfer the attributes of one or two face organs in the foreground region leaving the background region unchanged. To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background. Our method involves warping the reference photo to match the shape, pose, location, and expression of the input image. The fusion of the warped reference image and input image is then taken as the initialized image for a neural style transfer algorithm. Our method achieves better performance in terms of inception score (3.81) and Fréchet inception distance (80.31), which is about 10% higher than those of competitors, indicating that our framework is capable of producing high-quality and photorealistic attribute transfer results. Both theoretical findings and experimental results are provided to demonstrate the efficacy of the proposed framework, reveal its superiority over other state-of-the-art alternatives.https://www.mdpi.com/1099-4300/23/5/615face attribute transferimage warpingimage fusionfacial landmark detection |
| spellingShingle | Yuanbin Fu Jiayi Ma Xiaojie Guo A Foreground-Aware Framework for Local Face Attribute Transfer Entropy face attribute transfer image warping image fusion facial landmark detection |
| title | A Foreground-Aware Framework for Local Face Attribute Transfer |
| title_full | A Foreground-Aware Framework for Local Face Attribute Transfer |
| title_fullStr | A Foreground-Aware Framework for Local Face Attribute Transfer |
| title_full_unstemmed | A Foreground-Aware Framework for Local Face Attribute Transfer |
| title_short | A Foreground-Aware Framework for Local Face Attribute Transfer |
| title_sort | foreground aware framework for local face attribute transfer |
| topic | face attribute transfer image warping image fusion facial landmark detection |
| url | https://www.mdpi.com/1099-4300/23/5/615 |
| work_keys_str_mv | AT yuanbinfu aforegroundawareframeworkforlocalfaceattributetransfer AT jiayima aforegroundawareframeworkforlocalfaceattributetransfer AT xiaojieguo aforegroundawareframeworkforlocalfaceattributetransfer AT yuanbinfu foregroundawareframeworkforlocalfaceattributetransfer AT jiayima foregroundawareframeworkforlocalfaceattributetransfer AT xiaojieguo foregroundawareframeworkforlocalfaceattributetransfer |