Image-based virtual try-on involves generating an image of a person wearing a given clothing. Existing virtual try-on works suffer from the problem of misaligned regions between the predicted segmentation map and the deformed clothing, and the generation results of try-on are unnatural. To address this issue, we refine the definition of the misaligned regions and propose a high-resolution virtual try-on network called CS-VITON. The network adopts a two-stage strategy. The first stage is called the condition generator, which predicts the target segmentation map while deforming the clothing into shapes that match the human body. A component that measures the difference between the generated segmentation maps and the mask of deformed clothing is added to the loss function of the deep network. The component is well matched with the tasks of this stage, resulting in more reasonable necklines and skin boundaries. The second stage is called the try-on generator, in which the process of generating try-on images is modulated using residual blocks constructed based on style-preserved modulation. The modulation process takes into account the specific contextual style of the image, which improves the realism of the try-on results. Extensive experiments were conducted on a common high-resolution virtual try-on dataset, demonstrating that that our method yields more realistic virtual try-on results. Metrics such as kernel inception distance also showed some improvement. The code will be available soon at https://github.com/xinz626/CS-VITON.

基于图像的虚拟试穿涉及生成穿着给定服装的人的图像。现有的虚拟试穿作品存在预测分割图与变形服装区域未对齐的问题，并且试穿的生成结果不自然。为了解决这个问题，我们细化了未对齐区域的定义，并提出了一种称为 CS-VITON 的高分辨率虚拟试穿网络。该网络采用两阶段策略。第一阶段称为条件生成器，它预测目标分割图，同时将服装变形为与人体相匹配的形状。测量生成的分割图与变形服装掩模之间差异的组件被添加到深度网络的损失函数中。该组件与此阶段的任务很好匹配，导致领口和皮肤边界更加合理。第二阶段称为试穿生成器，其中使用基于风格保留调制构造的残差块来调制试穿图像的生成过程。调制过程考虑了图像的特定上下文风格，从而提高了试穿结果的真实感。在常见的高分辨率虚拟试穿数据集上进行了广泛的实验，证明我们的方法可以产生更真实的虚拟试穿结果。内核起始距离等指标也显示出一些改进。该代码即将在 https://github.com/xinz626/CS-VITON 上提供。