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.
翻译:虚拟装配室对于电子商务平台和时装设计师来说是一项具有挑战性但有用的任务。 现有的作品只能探测极少数类型的时装项目。 除了在改变所选时装项目的纹理和风格方面做得不好之外, 在这个项目中, 我们提出一种新的方法来解决这个问题。 我们首先使用面具 R- CNN 来寻找不同时装项目的区域, 其次使用神经风格传输来改变所选时装项目的风格。 我们使用的数据集由PaperDoll数据集和eBay's ModaNet提供的说明组成。 我们培训了8个模型和我们最好的模型,在数量和质量上都大大超过模型的基线模型, 其中68.72% MAP, 0.2% ASDR。