论文标题
最佳纹理：快速，稳健的纹理综合和样式通过最佳传输
Optimal Textures: Fast and Robust Texture Synthesis and Style Transfer through Optimal Transport
论文作者
论文摘要
本文提出了一种轻巧的高质量纹理合成算法，该算法很容易概括为其他应用，例如样式传输和纹理混合。我们通过自动编码器的瓶颈层中的深神经激活向量表示纹理特征，并将纹理合成问题构架为合成图像的激活值与示例纹理的激活值之间的最佳传输。为了找到此最佳传输映射，我们利用了N维概率密度函数（PDF）传输过程，该过程在PDF基础的多个随机旋转上迭代，并匹配每个维度跨每个维度的1D边缘分布。这可以在基于昂贵的后传播的神经纹理合成方法中获得质量和灵活性，但具有实现互动率的潜力。我们证明，一阶统计信息比当今使用的二阶统计信息提供了更强大的纹理表示形式。我们提出了这种算法的扩展，以降低神经特征空间的维度。我们利用多尺度的粗到精细合成金字塔来捕获和保留更大的图像特征。在一个框架下统一颜色和样式转移；并通过一种新型的掩蔽方案进一步增强了该系统，该方案重新示例并重新塑造了用户引导的纹理绘画和目标样式转移的功能分布。
This paper presents a light-weight, high-quality texture synthesis algorithm that easily generalizes to other applications such as style transfer and texture mixing. We represent texture features through the deep neural activation vectors within the bottleneck layer of an auto-encoder and frame the texture synthesis problem as optimal transport between the activation values of the image being synthesized and those of an exemplar texture. To find this optimal transport mapping, we utilize an N-dimensional probability density function (PDF) transfer process that iterates over multiple random rotations of the PDF basis and matches the 1D marginal distributions across each dimension. This achieves quality and flexibility on par with expensive back-propagation based neural texture synthesis methods, but with the potential of achieving interactive rates. We demonstrate that first order statistics offer a more robust representation for texture than the second order statistics that are used today. We propose an extension of this algorithm that reduces the dimensionality of the neural feature space. We utilize a multi-scale coarse-to-fine synthesis pyramid to capture and preserve larger image features; unify color and style transfer under one framework; and further augment this system with a novel masking scheme that re-samples and re-weights the feature distribution for user-guided texture painting and targeted style transfer.
