Image-based clothes changing system

Computational Visual Media

Hao-Tian Zhang¹  Zhao-Heng Zheng²  Fang-Lue Zhang³  Tai-Jiang Mu⁴ 

[1] Computer Science Department, Stanford University;Computer Science and Engineering, University of Michigan;School of Engineering and Computer Science, Victoria University of Wellington;TNList, Tsinghua University;

关键词: clothing try-on;    image warping;    human segmentation;   

DOI  :  10.1007/s41095-017-0084-6

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown