期刊
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
卷 -, 期 -, 页码 275-283出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3343031.3351075
关键词
Virtual try-on; image synthesis; pose transformation; semantic-guided learning
资金
- Ministry of Science and Technology of Taiwan [MOST-108-2634-F-009-006, MOST-108-2218-E-009-050, MOST-108-2823-8-002-004, MOST-108-2745-8-009-002, MOST-108-2634-F-007-009, MOST-107-2218-E-009-062, MOST-107-2218-E-002-010]
The image-based virtual try-on system has attracted a lot of research attention. The virtual try-on task is challenging since synthesizing try-on images involves the estimation of 3D transformation from 2D images, which is an ill-posed problem. Therefore, most of the previous virtual try-on systems cannot solve difficult cases, e.g., body occlusions, wrinkles of clothes, and details of the hair. Moreover, the existing systems require the users to upload the image for the target pose, which is not user-friendly. In this paper, we aim to resolve the above challenges by proposing a novel FashionOn network to synthesize user images fitting different clothes in arbitrary poses to provide comprehensive information about how suitable the clothes are. Specifically, given a user image, an in-shop clothing image, and a target pose (can be arbitrarily manipulated by joint points), FashionOn learns to synthesize the try-on images by three important stages: pose-guided parsing translation, segmentation region coloring, and salient region refinement. Extensive experiments demonstrate that FashionOn maintains the details of clothing information (e.g., logo, pleat, lace), as well as resolves the body occlusion problem, and thus achieves the state-of-the-art virtual try-on performance both qualitatively and quantitatively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据