clothing try-on, image warping, human segmentation
Current image-editing tools do not match up to the demands of personalized image manipulation, one application of which is changing clothes in user-captured 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.
Tsinghua University Press
Zhao-Heng Zheng, Hao-Tian Zhang, Fang-Lue Zhang et al. Image-based clothes changing system. Computational Visual Media 2017, 3(4): 337-347.