high performance computing on graphics processing units: hgpu.org

Programmable graphics hardware makes it possible to generate procedural noise textures on the fly for interactive rendering. However, filtering and antialiasing procedural noise involves a tradeoff between aliasing artifacts and loss of detail. In this paper we present a technique, targeted at interactive applications, that provides high-quality anisotropic filtering for noise textures. We generate noise tiles directly in the frequency domain by partitioning the frequency domain into oriented subbands. We then compute weighted sums of the subband textures to accurately approximate noise with a desired spectrum. This allows us to achieve high-quality anisotropic filtering. Our approach is based solely on 2D textures, avoiding the memory overhead of techniques based on 3D noise tiles. We devise a technique to compensate for texture distortions to generate uniform noise on arbitrary meshes. We develop a GPU-based implementation of our technique that achieves similar rendering performance as state-of-the-art algorithms for procedural noise. In addition, it provides anisotropic filtering and achieves superior image quality.