Back to Search
Start Over
Image-based clothes changing system
- Source :
- Computational Visual Media, Vol 3, Iss 4, Pp 337-347 (2017)
- Publication Year :
- 2017
- Publisher :
- SpringerOpen, 2017.
-
Abstract
- 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.
Details
- Language :
- English
- ISSN :
- 20960433 and 20960662
- Volume :
- 3
- Issue :
- 4
- Database :
- Directory of Open Access Journals
- Journal :
- Computational Visual Media
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.b9ca336d10e548a1a924e3ac37bbdc59
- Document Type :
- article
- Full Text :
- https://doi.org/10.1007/s41095-017-0084-6