Virtual try-on is a promising computer vision topic with a high commercial value wherein a new garment is visually worn on a person with a photo-realistic effect. Previous studies conduct their shape and content inference at one stage, employing a single-scale warping mechanism and a relatively unsophisticated content inference mechanism. These approaches have led to suboptimal results in terms of garment warping and skin reservation under challenging try-on scenarios. To address these limitations, we propose a novel virtual try-on method via progressive inference paradigm (PGVTON) that leverages a top-down inference pipeline and a general garment try-on strategy. Specifically, we propose a robust try-on parsing inference method by disentangling semantic categories and introducing consistency. Exploiting the try-on parsing as the shape guidance, we implement the garment try-on via warping-mapping-composition. To facilitate adaptation to a wide range of try-on scenarios, we adopt a covering more and selecting one warping strategy and explicitly distinguish tasks based on alignment. Additionally, we regulate StyleGAN2 to implement re-naked skin inpainting, conditioned on the target skin shape and spatial-agnostic skin features. Experiments demonstrate that our method has state-of-the-art performance under two challenging scenarios. The code will be available at https://github.com/NerdFNY/PGVTON.

翻译：虚拟试穿是一个具有高商业价值的计算机视觉研究课题，旨在以逼真的视觉效果将新服装穿在人物图像上。现有方法通常采用单阶段推理方式同时完成形状和内容推断，并依赖单尺度形变机制及相对简单的内容推断机制。这些方法在复杂试穿场景下易导致服装形变与皮肤保留效果欠佳。针对上述问题，本文提出一种基于渐进推理范式的虚拟试穿方法（PGVTON），采用自上而下的推理流程及通用服装试穿策略。具体地，我们通过解耦语义类别并引入一致性约束，提出鲁棒的试穿解析推理方法。以试穿解析作为形状引导，通过形变-映射-合成三阶段实现服装试穿。为适应多样化试穿场景，我们采用"先覆盖再筛选"的形变策略，并根据对齐程度显式区分任务类型。此外，我们通过调节StyleGAN2实现条件性裸露皮肤修复，该修复过程以目标皮肤形状和空间无关的皮肤特征为条件。实验表明，本方法在两类挑战性场景下均达到最优性能。代码将开源至https://github.com/NerdFNY/PGVTON。