Self-supervised 3D Face Reconstruction Based on Detailed Face Mask
Self-supervised 3D face reconstruction can alleviate the problem of lack of 3D face data,and has therefore become a hot research topic in recent years.Existing self-supervised methods usually focus on using globally supervised signals and do not pay enough attention to the local details of faces.In...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2023-02-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-2-214.pdf |
| _version_ | 1797845082278199296 |
|---|---|
| author | ZHU Lei, WANG Shanmin, LIU Qingshan |
| author_facet | ZHU Lei, WANG Shanmin, LIU Qingshan |
| author_sort | ZHU Lei, WANG Shanmin, LIU Qingshan |
| collection | DOAJ |
| description | Self-supervised 3D face reconstruction can alleviate the problem of lack of 3D face data,and has therefore become a hot research topic in recent years.Existing self-supervised methods usually focus on using globally supervised signals and do not pay enough attention to the local details of faces.In order to better recover fine-grained 3D faces with vivid details,this paper proposes a fine-grained 3D face reconstruction method based on face part masks,which can reconstruct fine-grained 3D faces without any 3D face annotation.The main idea is to improve the local accuracy of the reconstructed 3D face by giving refinement constraints on the face region through the face part mask and self-supervised constraints on the face part mask on top of the basic loss functions such as 2D image consistency loss,image deep perception loss,etc.Qualitative and quantitative experiments on AFLW2000-3D and MICC Florence datasets demonstrate the effectiveness and superiority of the proposed method. |
| first_indexed | 2024-04-09T17:33:54Z |
| format | Article |
| id | doaj.art-aad7a2e2a77a42a2b84f799bf058a92e |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:54Z |
| publishDate | 2023-02-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-aad7a2e2a77a42a2b84f799bf058a92e2023-04-18T02:33:17ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2023-02-0150221422010.11896/jsjkx.220600035Self-supervised 3D Face Reconstruction Based on Detailed Face MaskZHU Lei, WANG Shanmin, LIU Qingshan01 Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing University of Information Science, Technology,Nanjing210044,China ;2 College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,ChinaSelf-supervised 3D face reconstruction can alleviate the problem of lack of 3D face data,and has therefore become a hot research topic in recent years.Existing self-supervised methods usually focus on using globally supervised signals and do not pay enough attention to the local details of faces.In order to better recover fine-grained 3D faces with vivid details,this paper proposes a fine-grained 3D face reconstruction method based on face part masks,which can reconstruct fine-grained 3D faces without any 3D face annotation.The main idea is to improve the local accuracy of the reconstructed 3D face by giving refinement constraints on the face region through the face part mask and self-supervised constraints on the face part mask on top of the basic loss functions such as 2D image consistency loss,image deep perception loss,etc.Qualitative and quantitative experiments on AFLW2000-3D and MICC Florence datasets demonstrate the effectiveness and superiority of the proposed method.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-2-214.pdf3d face reconstruction|face alignment|face modeling|self-supervised learning|face rendering |
| spellingShingle | ZHU Lei, WANG Shanmin, LIU Qingshan Self-supervised 3D Face Reconstruction Based on Detailed Face Mask Jisuanji kexue 3d face reconstruction|face alignment|face modeling|self-supervised learning|face rendering |
| title | Self-supervised 3D Face Reconstruction Based on Detailed Face Mask |
| title_full | Self-supervised 3D Face Reconstruction Based on Detailed Face Mask |
| title_fullStr | Self-supervised 3D Face Reconstruction Based on Detailed Face Mask |
| title_full_unstemmed | Self-supervised 3D Face Reconstruction Based on Detailed Face Mask |
| title_short | Self-supervised 3D Face Reconstruction Based on Detailed Face Mask |
| title_sort | self supervised 3d face reconstruction based on detailed face mask |
| topic | 3d face reconstruction|face alignment|face modeling|self-supervised learning|face rendering |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-2-214.pdf |
| work_keys_str_mv | AT zhuleiwangshanminliuqingshan selfsupervised3dfacereconstructionbasedondetailedfacemask |