基于纹理特征预设的轻量级纹理迁移
Lightweight texture transfer based on texture feature preset
AI总结：
针对纹理迁移中纹理特征高度重复导致模型冗余的问题，提出基于纹理特征预设的轻量级方法，通过预设通用纹理特征图避免重复编码，在保持高质量结果的同时大幅减小模型规模并加速推理。
摘要：
在纹理迁移任务中，参考纹理图像通常表现出高度重复的纹理特征，并且同一风格下不同内容图像的纹理迁移结果也共享非常相似的纹理模式。编码这种高度相似的纹理特征通常需要深层网络和大量通道，这也是整个模型参数数量、计算负载和推理时间的主要来源。我们提出了一种基于纹理特征预设（TFP）的轻量级纹理迁移方法。TFP充分利用纹理特征的高重复性，为给定风格提供预设的通用纹理特征图。这些预设特征图可以直接与任意内容的浅层颜色迁移特征图进行融合和解码，生成纹理迁移结果，从而避免冗余纹理信息的重复编码。我们预设的纹理特征图是通过具有一致分布（标准正态分布）的噪声输入图像编码得到的。这种一致的输入分布可以完全避免纹理迁移差异性问题，并且通过随机采样不同的噪声输入，我们可以在同一参考风格下获得不同的纹理特征和纹理迁移结果。与最先进的技术相比，我们的TFP不仅产生了视觉上更优的结果，还将模型大小减少了3.2-3538倍，并将处理速度提高了1.8-5.6倍。
英文摘要：
In the task of texture transfer, reference texture images typically exhibit highly repetitive texture features, and the texture transfer results from different content images under the same style also share remarkably similar texture patterns. Encoding such highly similar texture features often requires deep layers and a large number of channels, making it is also the main source of the entire model's parameter count and computational load, and inference time. We propose a lightweight texture transfer based on texture feature preset (TFP). TFP takes full advantage of the high repetitiveness of texture features by providing preset universal texture feature maps for a given style. These preset feature maps can be fused and decoded directly with shallow color transfer feature maps of any content to generate texture transfer results, thereby avoiding redundant texture information from being encoded repeatedly. The texture feature map we preset is encoded through noise input images with consistent distribution (standard normal distribution). This consistent input distribution can completely avoid the problem of texture transfer differentiation, and by randomly sampling different noise inputs, we can obtain different texture features and texture transfer results under the same reference style. Compared to state-of-the-art techniques, our TFP not only produces visually superior results but also reduces the model size by 3.2-3538 times and speeds up the process by 1.8-5.6 times.
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。
