This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high quality 3D data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as "slices" are generated during the training stage. These synthetic textures are compared to exemplar images via a perceptual loss function based on a pre-trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for $256^3$ voxels) on a single GPU. Integrated with a spatially seeded PRNG the proposed generator network directly returns an RGB value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state-of-the-art patch based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.

中文翻译：

---

使用深度 3D 网络的按需实体纹理合成

本文描述了一种基于深度学习框架的按需体积纹理合成的新方法，该框架允许以交互速率生成高质量的 3D 数据。基于一些纹理的示例图像，训练生成网络以合成任意大小的实体纹理的连贯部分，这些部分沿某些方向再现示例的视觉特征。为了应对 GPU 上的高分辨率和 3D 处理固有的内存限制和计算复杂性，在训练阶段仅生成称为“切片”的 2D 纹理。这些合成纹理通过基于预训练深度网络的感知损失函数与示例图像进行比较。建议的网络非常轻（小于 100k 参数），因此，它只需要可持续的训练（即几个小时），并且能够在单个 GPU 上非常快速地生成（大约 1 秒，256^3 美元体素）。与空间种子 PRNG 集成，建议的生成器网络直接返回给定一组 3D 坐标的 RGB 值。合成的体积具有良好的视觉效果，至少相当于最先进的基于补丁的方法。它们自然可以无缝平铺，并且可以完全并行生成。合成的体积具有良好的视觉效果，至少相当于最先进的基于补丁的方法。它们自然可以无缝平铺，并且可以完全并行生成。合成的体积具有良好的视觉效果，至少相当于最先进的基于补丁的方法。它们自然可以无缝平铺，并且可以完全并行生成。