Generating natural textures is a challenging task in graphics and virtual reality. Leaf texture is an important part of natural textures. Different from many other textures with repetitive and random patterns, leaves are closely related to its botanic structures, especially veins. Appearing in forms of foliages in the wild, the variety of leaf textures produces the realism of virtual scenes. In this paper, we propose a novel leaf-texturing method that models the inherent relevance between structural features and pattern distributions. Based on the structure-guided model, we design an example-based algorithm to extract and generate leaf textures depending on venation structures. Global variations and local details are processed separately for multi-scale texture features. Experiments show that our model produces visually plausible leaf textures with variations, which can be easily applied to many other applications, including texture transfer between different leaf structures, aging effect and texture editing.

在图形和虚拟现实中，生成自然纹理是一项艰巨的任务。叶纹理是自然纹理的重要组成部分。与许多具有重复和随机图案的其他纹理不同，叶子与其植物结构（尤其是静脉）密切相关。在野外以叶子形式出现时，各种各样的叶子纹​​理产生了虚拟场景的真实感。在本文中，我们提出了一种新颖的叶子纹理化方法，该方法对结构特征和图案分布之间的内在关联性进行建模。基于结构指导模型，我们设计了一个基于示例的算法来提取和生成取决于纹理结构的叶片纹理。对于多尺度纹理特征，将分别处理全局变化和局部细节。