One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns
This work addresses the need for unified noise generation in computer graphics, offering a novel approach that is incremental in improving procedural material design.
The paper tackles the problem of generating multiple types of procedural noise textures separately by introducing a single generative model that can learn to generate, blend, and produce spatially-varying noise patterns, resulting in higher-fidelity material reconstructions without prior knowledge of noise type.
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.