arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04104cs.CV
收藏

基于图像的虚拟试衣间

Image-based Virtual Fitting Room

Stanford University(斯坦福大学)

Zhiling Huang, Junwen Bu, Jie Chen

摘要:

虚拟试衣间对于电子商务平台和服装设计师来说是一项具有挑战性的任务,但也是一项有用的功能。现有的作品只能检测很少类型的时尚物品。此外,他们在改变所选时装的质地和风格方面做得很差。在这个项目中,我们提出了一种新的方法来解决这个问题。我们首先使用Mask R-CNN来找到不同时尚单品的区域,然后使用神经风格转移来改变所选时尚单品的风格。我们使用的数据集由PaperDoll数据集的图像和eBay的ModaNet提供的注释组成。我们训练了8个模型,我们最好的模型在定量和定性上都大大优于基线模型,mAP为68.72%,ASDR为0.2%。

英文摘要:

Virtual fitting room is a challenging task yet useful feature for e-commerce platforms and fashion designers. Existing works can only detect very few types of fashion items. Besides they did poorly in changing the texture and style of the selected fashion items. In this project, we propose a novel approach to address this problem. We firstly used Mask R-CNN to find the regions of different fashion items, and secondly used Neural Style Transfer to change the style of the selected fashion items. The dataset we used is composed of images from PaperDoll dataset and annotations provided by eBay's ModaNet. We trained 8 models and our best model massively outperformed baseline models both quantitatively and qualitatively, with 68.72% mAP, 0.2% ASDR.

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。

↑