Image-based clothes changing system
Abstract Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods. In this paper, we propose an image-based...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-05-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41095-017-0084-6 |
| _version_ | 1818973941983608832 |
|---|---|
| author | Zhao-Heng Zheng Hao-Tian Zhang Fang-Lue Zhang Tai-Jiang Mu |
| author_facet | Zhao-Heng Zheng Hao-Tian Zhang Fang-Lue Zhang Tai-Jiang Mu |
| author_sort | Zhao-Heng Zheng |
| collection | DOAJ |
| description | Abstract Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods. In this paper, we propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping. Image segmentation and mask generation are first applied to the user input. Afterwards, we determine joint positions via a neural network. Then, body shape matching is performed and the shape of the model is warped to the user’s shape. Finally, head swapping is performed to produce realistic virtual results. We also provide a supervision and labeling tool for refinement and further assistance when creating a dataset. |
| first_indexed | 2024-12-20T15:32:10Z |
| format | Article |
| id | doaj.art-b9ca336d10e548a1a924e3ac37bbdc59 |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-12-20T15:32:10Z |
| publishDate | 2017-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-b9ca336d10e548a1a924e3ac37bbdc592022-12-21T19:35:35ZengSpringerOpenComputational Visual Media2096-04332096-06622017-05-013433734710.1007/s41095-017-0084-6Image-based clothes changing systemZhao-Heng Zheng0Hao-Tian Zhang1Fang-Lue Zhang2Tai-Jiang Mu3Computer Science and Engineering, University of MichiganComputer Science Department, Stanford UniversitySchool of Engineering and Computer Science, Victoria University of WellingtonTNList, Tsinghua UniversityAbstract Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in usercaptured images. Previous work can change single color clothes using parametric human warping methods. In this paper, we propose an image-based clothes changing system, exploiting body factor extraction and content-aware image warping. Image segmentation and mask generation are first applied to the user input. Afterwards, we determine joint positions via a neural network. Then, body shape matching is performed and the shape of the model is warped to the user’s shape. Finally, head swapping is performed to produce realistic virtual results. We also provide a supervision and labeling tool for refinement and further assistance when creating a dataset.http://link.springer.com/article/10.1007/s41095-017-0084-6clothing try-onimage warpinghuman segmentation |
| spellingShingle | Zhao-Heng Zheng Hao-Tian Zhang Fang-Lue Zhang Tai-Jiang Mu Image-based clothes changing system Computational Visual Media clothing try-on image warping human segmentation |
| title | Image-based clothes changing system |
| title_full | Image-based clothes changing system |
| title_fullStr | Image-based clothes changing system |
| title_full_unstemmed | Image-based clothes changing system |
| title_short | Image-based clothes changing system |
| title_sort | image based clothes changing system |
| topic | clothing try-on image warping human segmentation |
| url | http://link.springer.com/article/10.1007/s41095-017-0084-6 |
| work_keys_str_mv | AT zhaohengzheng imagebasedclotheschangingsystem AT haotianzhang imagebasedclotheschangingsystem AT fangluezhang imagebasedclotheschangingsystem AT taijiangmu imagebasedclotheschangingsystem |