We present a set of optimizations that improve the performance of high-quality volumetric path tracing. We build upon unbiased volume sampling techniques, i.e., null-collision trackers, with voxel data stored in an OpenVDB tree. The presented optimizations achieve an overall 2x to 3x speedup when implemented on a modern GPU, with an approximately 6.5x reduction in memory footprint. The improvements primarily stem from a multi-level digital differential analyzer (DDA) to step through a grid of precomputed bounds; a replacement of the top levels of the OpenVDB tree with a dense indirection texture, similar to virtual textures, while preserving some sparsity; and quantization of the voxel data, encoded using GPU-supported block compression. Finally, we examine the isolated effect of our optimizations, covering stochastic filtering, the use of dense indirection textures, compressed voxel data, and singleversus multi-level DDAs.
Our website uses cookies and similar technologies.
Some cookies are necessary for visiting this website, i.e. essential. Otherwise, without these cookies, your end device would not be able to remember your privacy choices, for example.
If you agree, we also use cookies and data to measure your interactions with our website or to integrate external media (e.g. videos).
You can view and withdraw your consent at any time at Privacy policy. On the site you will also find additional information about the cookies and technologies used.
Here you will find an overview of all cookies used. You can give your consent to whole categories or display further information and select certain cookies.
