Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing
Facial makeup transfer is a special form of image style transfer. For the reference makeup image with large-pose, improving the quality of the image generated after makeup transfer is still a challenging problem worthy of discussion. In this paper, a large-pose makeup transfer algorithm based on gen...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-01-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023034?viewType=HTML |
| _version_ | 1811333244685123584 |
|---|---|
| author | Qiming Li Tongyue Tu |
| author_facet | Qiming Li Tongyue Tu |
| author_sort | Qiming Li |
| collection | DOAJ |
| description | Facial makeup transfer is a special form of image style transfer. For the reference makeup image with large-pose, improving the quality of the image generated after makeup transfer is still a challenging problem worthy of discussion. In this paper, a large-pose makeup transfer algorithm based on generative adversarial network (GAN) is proposed. First, a face alignment module (FAM) is introduced to locate the key points, such as the eyes, mouth and skin. Secondly, a face parsing module (FPM) and face parsing losses are designed to analyze the source image and extract the face features. Then, the makeup style code is extracted from the reference image and the makeup transfer is completed through integrating facial features and makeup style code. Finally, a large-pose makeup transfer (LPMT) dataset is collected and constructed. Experiments are carried out on the traditional makeup transfer (MT) dataset and the new LPMT dataset. The results show that the image quality generated by the proposed method is better than that of the latest method for large-pose makeup transfer. |
| first_indexed | 2024-04-13T16:49:02Z |
| format | Article |
| id | doaj.art-1a881206413844b0830e041fa0515db4 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-13T16:49:02Z |
| publishDate | 2023-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-1a881206413844b0830e041fa0515db42022-12-22T02:38:59ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-0120173775710.3934/mbe.2023034Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsingQiming Li 0Tongyue Tu1Department of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaFacial makeup transfer is a special form of image style transfer. For the reference makeup image with large-pose, improving the quality of the image generated after makeup transfer is still a challenging problem worthy of discussion. In this paper, a large-pose makeup transfer algorithm based on generative adversarial network (GAN) is proposed. First, a face alignment module (FAM) is introduced to locate the key points, such as the eyes, mouth and skin. Secondly, a face parsing module (FPM) and face parsing losses are designed to analyze the source image and extract the face features. Then, the makeup style code is extracted from the reference image and the makeup transfer is completed through integrating facial features and makeup style code. Finally, a large-pose makeup transfer (LPMT) dataset is collected and constructed. Experiments are carried out on the traditional makeup transfer (MT) dataset and the new LPMT dataset. The results show that the image quality generated by the proposed method is better than that of the latest method for large-pose makeup transfer.https://www.aimspress.com/article/doi/10.3934/mbe.2023034?viewType=HTMLmakeup transfergenerative adversarial networklarge-pose faceface parsingface alignment |
| spellingShingle | Qiming Li Tongyue Tu Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing Mathematical Biosciences and Engineering makeup transfer generative adversarial network large-pose face face parsing face alignment |
| title | Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| title_full | Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| title_fullStr | Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| title_full_unstemmed | Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| title_short | Large-pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| title_sort | large pose facial makeup transfer based on generative adversarial network combined face alignment and face parsing |
| topic | makeup transfer generative adversarial network large-pose face face parsing face alignment |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023034?viewType=HTML |
| work_keys_str_mv | AT qimingli largeposefacialmakeuptransferbasedongenerativeadversarialnetworkcombinedfacealignmentandfaceparsing AT tongyuetu largeposefacialmakeuptransferbasedongenerativeadversarialnetworkcombinedfacealignmentandfaceparsing |