VOGUE: Try-On by StyleGAN Interpolation Optimization

Given an image of a target person and an image of another person wearing a garment, we automatically generate the target person in the given garment. At the core of our method is a pose-conditioned StyleGAN2 latent space interpolation, which seamlessly combines the areas of interest from each image, i.e., body shape, hair, and skin color are derived from the target person, while the garment with its folds, material properties, and shape comes from the garment image. By automatically optimizing for interpolation coefficients per layer in the latent space, we can perform a seamless, yet true to source, merging of the garment and target person. Our algorithm allows for garments to deform according to the given body shape, while preserving pattern and material details. Experiments demonstrate state-of-the-art photo-realistic results at high resolution (512×512).

https://arxiv.org/abs/2101.02285

给定一个人物以及另一个人物穿着目标衣服的图片,我们可以自动地生成目标人物穿着目标衣服的图像。我们方法的核心是一个基于姿态条件的StyleGAN2隐空间插值,这样的插值可以无缝地操作目标图像地感兴趣区域,例如体型,头发以及由目标人物获得的肤色,并且能保持衣物的褶皱,材料,质地以及形状。通过自动地优化每一层的插值系数,我们可以实现无缝的由原始图像到目标图像的衣物融合。我们的算法能够让衣物适应目标体型并且同时保持衣物材料的特征。实验表明我们的模型可以取得在高分辨率图像(512*512)生成任务上的SOTA效果。

发表评论

邮箱地址不会被公开。 必填项已用*标注