基于骨架的特征在虚拟试穿中的重要性
Significance of Skeleton-based Features in Virtual Try-On
AI总结：
针对虚拟试穿中手臂交叉姿势导致的服装变形不一致问题，提出基于骨架几何特征分割独立变形并结合合成器与掩码预测网络的无配对数据解决方案。
摘要：
虚拟试穿（VTON）的理念通过让用户在家中舒适地试穿服装，为电子零售带来了便利。通常，当一个人摆出双臂折叠（即弯曲或交叉）的姿势想要试穿一套服装时，大多数现有的VTON方法会产生不一致的结果。在长袖服装的情况下，问题变得更加严重。因为此时，对于交叉手臂的姿势，不同服装部分之间可能会发生重叠。现有的方法，特别是采用薄板样条（TPS）变换的基于变形的方法，无法处理此类情况。为此，我们尝试一种解决方案，将源人物的服装分割成具有语义意义的部分，并将每个部分独立地变形以适应目标人物的形状。为了解决弯曲问题，我们采用与人体几何一致的手工几何特征来对源服装进行变形。此外，我们提出了两个基于学习的模块：一个合成器网络和一个掩码预测网络。所有这些模块共同致力于在不需要任何配对训练数据的情况下，生成具有照片级真实感且姿态鲁棒的VTON解决方案。与一些基准方法的比较清楚地证明了该方法的有效性。
英文摘要：
The idea of \textit{Virtual Try-ON} (VTON) benefits e-retailing by giving an user the convenience of trying a clothing at the comfort of their home. In general, most of the existing VTON methods produce inconsistent results when a person posing with his arms folded i.e., bent or crossed, wants to try an outfit. The problem becomes severe in the case of long-sleeved outfits. As then, for crossed arm postures, overlap among different clothing parts might happen. The existing approaches, especially the warping-based methods employing \textit{Thin Plate Spline (TPS)} transform can not tackle such cases. To this end, we attempt a solution approach where the clothing from the source person is segmented into semantically meaningful parts and each part is warped independently to the shape of the person. To address the bending issue, we employ hand-crafted geometric features consistent with human body geometry for warping the source outfit. In addition, we propose two learning-based modules: a synthesizer network and a mask prediction network. All these together attempt to produce a photo-realistic, pose-robust VTON solution without requiring any paired training data. Comparison with some of the benchmark methods clearly establishes the effectiveness of the approach.
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。
