TGHop：一种可解释的高效轻量级纹理生成方法
TGHop: An Explainable, Efficient and Lightweight Method for Texture Generation
摘要：
提出了一种可解释的、高效的、轻量级的纹理生成方法TGHop（Texture Generation PixelHop的缩写）。虽然通过深度神经网络可以实现视觉上令人愉悦的纹理的合成，但是相关联的模型尺寸大，难以在理论上解释，并且在训练中计算昂贵。相比之下，TGHop的模型尺寸小，数学上透明，训练和推理效率高，并且能够生成高质量的纹理。给定一个示例性纹理，TGHop首先从中裁剪出许多样本面片，以形成称为源的样本面片集合。然后，它分析来自源的样本的像素统计，并通过使用PixelHop++框架获得这些补丁的从细到粗的子空间序列。为了使用TGHop生成纹理补丁，我们从称为核心的粗粒度子空间开始，并尝试通过遵循真实样本的分布来生成每个子空间中的样本。最后，纹理块拼接形成一个大尺寸的纹理图像。实验结果表明，TGHop能以较小的模型尺寸和较快的速度生成质量较高的纹理图像。
英文摘要：
An explainable, efficient and lightweight method for texture generation, called TGHop (an acronym of Texture Generation PixelHop), is proposed in this work. Although synthesis of visually pleasant texture can be achieved by deep neural networks, the associated models are large in size, difficult to explain in theory, and computationally expensive in training. In contrast, TGHop is small in its model size, mathematically transparent, efficient in training and inference, and able to generate high quality texture. Given an exemplary texture, TGHop first crops many sample patches out of it to form a collection of sample patches called the source. Then, it analyzes pixel statistics of samples from the source and obtains a sequence of fine-to-coarse subspaces for these patches by using the PixelHop++ framework. To generate texture patches with TGHop, we begin with the coarsest subspace, which is called the core, and attempt to generate samples in each subspace by following the distribution of real samples. Finally, texture patches are stitched to form texture images of a large size. It is demonstrated by experimental results that TGHop can generate texture images of superior quality with a small model size and at a fast speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
