arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09479cs.CV
收藏

高真实感虚拟试穿的非纠缠周期一致性

Disentangled Cycle Consistency for Highly-realistic Virtual Try-On

The University of Hong Kong(香港大学);Tencent AI Lab(腾讯AI实验室);ETH Zürich(苏黎世联邦理工学院);Tencent Data Platform(腾讯数据平台)

Chongjian Ge, Yibing Song, Yuying Ge, Han Yang, Wei Liu, Ping Luo

摘要:

图像虚拟试穿将人物图像上的衣服替换为期望的店内衣服图像。这是具有挑战性的,因为人和店内的衣服是不成对的。现有的方法将虚拟试穿制定为绘画或循环一致性。这两个公式都鼓励生成网络以自监督的方式重建输入图像。然而,现有的方法不区分服装和非服装区域。由于图像内容的严重耦合,直接生成会妨碍虚拟试穿质量。在本文中,我们提出了一个解纠缠的周期一致性尝试网络(DCTON)。DCTON能够通过解开虚拟试穿的重要组件(包括衣服翘曲、皮肤合成和图像合成)来产生高度逼真的试穿图像。为此,DCTON可以在循环一致性学习之后以自我监督的方式自然地训练。在具有挑战性的基准测试上进行的大量实验表明,DCTON的性能优于最先进的方法。

英文摘要:

Image virtual try-on replaces the clothes on a person image with a desired in-shop clothes image. It is challenging because the person and the in-shop clothes are unpaired. Existing methods formulate virtual try-on as either in-painting or cycle consistency. Both of these two formulations encourage the generation networks to reconstruct the input image in a self-supervised manner. However, existing methods do not differentiate clothing and non-clothing regions. A straight-forward generation impedes virtual try-on quality because of the heavily coupled image contents. In this paper, we propose a Disentangled Cycle-consistency Try-On Network (DCTON). The DCTON is able to produce highly-realistic try-on images by disentangling important components of virtual try-on including clothes warping, skin synthesis, and image composition. To this end, DCTON can be naturally trained in a self-supervised manner following cycle consistency learning. Extensive experiments on challenging benchmarks show that DCTON outperforms state-of-the-art approaches favorably.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑