一种噪声统领一切：学习空间变化噪声模式的统一模型
One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns
AI总结：
本文提出一种基于去噪扩散模型的统一生成模型，通过数据增强与网络条件化技术生成并混合多种程序化噪声，支持空间变化且无需此类训练数据，提升了逆向程序化材质设计的保真度。
摘要：
程序化噪声是计算机图形学管线的基础组件，提供了一种灵活的方式来生成展现“自然”随机变化的纹理。存在许多不同类型的噪声，每种都由独立的算法生成。在本文中，我们提出了一个单一的生成模型，该模型可以学习生成多种类型的噪声以及它们之间的混合。此外，尽管在训练时无法获取此类数据，它仍能产生空间变化的噪声混合。这些特性是通过使用数据增强和网络条件化技术的新颖组合来训练去噪扩散模型而实现的。与程序化噪声生成器类似，该模型的行为可以通过可解释的参数和随机源进行控制。我们使用我们的模型生成了各种视觉上引人注目的噪声纹理。我们还展示了我们的模型在改进逆向程序化材质设计中的应用；在程序化材质图中，使用我们的模型代替固定类型的噪声节点，可以在无需预先知道噪声类型的情况下，实现更高保真度的材质重建。
英文摘要：
Procedural noise is a fundamental component of computer graphics pipelines, offering a flexible way to generate textures that exhibit "natural" random variation. Many different types of noise exist, each produced by a separate algorithm. In this paper, we present a single generative model which can learn to generate multiple types of noise as well as blend between them. In addition, it is capable of producing spatially-varying noise blends despite not having access to such data for training. These features are enabled by training a denoising diffusion model using a novel combination of data augmentation and network conditioning techniques. Like procedural noise generators, the model's behavior is controllable via interpretable parameters and a source of randomness. We use our model to produce a variety of visually compelling noise textures. We also present an application of our model to improving inverse procedural material design; using our model in place of fixed-type noise nodes in a procedural material graph results in higher-fidelity material reconstructions without needing to know the type of noise in advance.
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。
