Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering

TL;DR

Gabor Fields introduce an orientation-selective, multi-scale volume representation that improves rendering efficiency and quality by enabling continuous filtering, hierarchical pruning, and procedural volume design, addressing limitations of Gaussian-based volume methods.

Contribution

The paper presents Gabor Fields, a novel orientation-selective mixture of Gabor kernels that allows continuous frequency filtering and hierarchical pruning for Gaussian-based volume rendering.

Findings

Enables smooth hierarchical levels of detail in volume rendering.

Reduces rendering time by selective pruning of frequency primitives.

Facilitates efficient procedural cloud rendering using Gabor-noise modulation.

Abstract

Gaussian-based representations have enabled efficient physically-based volume rendering at a fraction of the memory cost of regular, discrete, voxel-based distributions. However, several remaining issues hamper their widespread use. One of the advantages of classic voxel grids is the ease of constructing hierarchical representations by either storing volumetric mipmaps or selectively pruning branches of an already hierarchical voxel grid. Such strategies reduce rendering time and eliminate aliasing when lower levels of detail are required. Constructing similar strategies for Gaussian-based volumes is not trivial. Straightforward solutions, such as prefiltering or computing mipmap-style representations, lead to increased memory requirements or expensive re-fitting of each level separately. Additionally, such solutions do not guarantee a smooth transition between different hierarchy levels. To address these limitations, we propose Gabor Fields, an orientation-selective mixture of Gabor kernels that enables continuous frequency filtering at no cost. The frequency content of the asset is reduced by selectively pruning primitives, directly benefiting rendering performance. Beyond filtering, we demonstrate that stochastically sampling from different frequencies and orientations at each ray recursion enables masking substantial portions of the volume, accelerating ray traversal time in single- and multiple-scattering settings. Furthermore, inspired by procedural volumes, we present an application for efficient design and rendering of procedural clouds as Gabor-noise-modulated Gaussians.