The system of Virtual Try-ON (VTON) allows a user to try a product virtually. In general, a VTON system takes a clothing source and a person's image to predict the try-on output of the person in the given clothing. Although existing methods perform well for simple poses, in case of bent or crossed arms posture or when there is a significant difference between the alignment of the source clothing and the pose of the target person, these methods fail by generating inaccurate clothing deformations. In the VTON methods that employ Thin Plate Spline (TPS) based clothing transformations, this mainly occurs for two reasons - (1)~the second-order smoothness constraint of TPS that restricts the bending of the object plane. (2)~Overlaps among different clothing parts (e.g., sleeves and torso) can not be modeled by a single TPS transformation, as it assumes the clothing as a single planar object; therefore, disregards the independence of movement of different clothing parts. To this end, we make two major contributions. Concerning the bending limitations of TPS, we propose a human AnaTomy-Aware Geometric (ATAG) transformation. Regarding the overlap issue, we propose a part-based warping approach that divides the clothing into independently warpable parts to warp them separately and later combine them. Extensive analysis shows the efficacy of this approach.

翻译：虚拟试穿（VTON）系统允许用户虚拟试穿产品。通常，VTON系统利用服装源图像和人物图像来预测该人物穿着指定服装的试穿效果。尽管现有方法在简单姿态下表现良好，但当出现手臂弯曲或交叉姿态，或源服装与目标人物姿态对齐存在显著差异时，这些方法因生成不准确的服装形变而失效。在采用基于薄板样条（TPS）服装形变的VTON方法中，这一问题主要源于两个原因：（1）TPS的二阶光滑性约束限制了物体平面的弯曲；（2）不同服装部件（如衣袖与躯干）之间的重叠无法通过单一TPS形变建模，因为该方法将服装视为单一平面物体，从而忽略了不同服装部件运动的独立性。为此，我们做出两项主要贡献：针对TPS弯曲限制，提出了人体解剖感知几何（ATAG）形变方法；针对重叠问题，提出基于部件的扭曲方法，将服装划分为可独立扭曲的部件分别处理，随后合并结果。大量分析验证了该方法的有效性。