The goal of image-based virtual try-on is to generate an image of the target
person naturally wearing the given clothing. However, most existing methods
solely focus on the frontal try-on using the frontal clothing. When the views
of the clothing and person are significantly inconsiste
该研究提出一种新颖的基于 2D 和 3D 方法的单目 - 3D 虚拟试穿网络,通过有效地整合 2D 信息和学习将 2D 表示提升到 3D 的映射以构建一个 3D 试穿模型。所提出的模型包含三个模块:单目预测模块、深度细化模块和纹理融合模块。该模型在构建高质量的试衣数据集的基础上,通过大量实验,证明了其比其他 3D 方法更高效和能够更真实地描述试穿效果。