SketchHairSalon

SketchHairSalon，一个两阶段框架，用于直接从描绘所需头发结构和外观的手绘草图生成逼真的头发图像。在第一阶段，我们训练一个网络从输入的头发草图中预测头发遮罩，并带有一组可选的非头发笔触。在第二阶段，训练另一个网络从输入草图和生成的遮罩中合成头发图像的结构和外观。为了使两个阶段的网络意识到笔画的长期依赖性，我们对它们应用了自我注意模块。为了训练这些网络，我们提出了一个新的数据集，其中包含数千个带注释的头发草图图像对和相应的头发遮罩。

SketchHairSalon is a two-stage framework for generating photorealistic hair images directly from hand-drawn sketches that depict the desired structure and appearance of hair. In the first stage, we train a network to predict hair masks from input hair sketches, alongside a set of optional non-hair strokes. In the second stage, another network is trained to synthesize the structure and appearance of hair images from the input sketches and the generated masks. To enable the two-stage networks to capture long-range dependencies of strokes, we apply self-attention modules to them. For training these networks, we propose a novel dataset comprising thousands of annotated paired hair sketch-image pairs and their corresponding hair masks.