State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such representations capture rich structures in texture images, outperforming wavelet-based representations in this regard. However, conversely to neural networks, wavelets offer meaningful representations, as they are known to detect structures at multiple scales (e.g. edges) in images. In this work, we propose a family of statistics built upon non-linear wavelet based representations, that can be viewed as a particular instance of a one-layer CNN, using a generalized rectifier non-linearity. These statistics significantly improve the visual quality of previous classical wavelet-based models, and allow one to produce syntheses of similar quality to state-of-the-art models, on both gray-scale and color textures.
翻译:用于质谱合成的最先进的最大恒温模型来自依靠进化神经网络(CNN)所定义的图像表达方式的统计数据。这种表示方式收集了质谱图像中的丰富结构,在这方面的表达方式优于以波浪为基础的表达方式。然而,与神经网络相反,波子提供了有意义的表达方式,因为人们知道它们能够在多个尺度(例如边缘)探测图像中的结构。在这项工作中,我们建议建立一个以非线性波谱为基础的表达方式为基础的统计体系,该体系可以被看作一个单层CNN的特例,使用一种通用的校准非线性非线性。这些统计数据极大地改进了以往古典波谱模型的视觉质量,并允许一种在灰度和颜色纹理上生成与最新模型质量相似的合成。