One Noise to Rule Them All: Learning a Unified Model of Spatially-Varying Noise Patterns

arXiv:2404.16292v1 Announce Type: cross
Abstract: 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 …

abstract algorithm arxiv computer computer graphics cs.cv cs.gr cs.lg fundamental generate graphics natural noise paper patterns pipelines random them type types unified model variation