Multi-level ray tracing algorithm

By A. Reshetov, Alexei Soupikov, Jim Hurley. ACM Transactions on Graphics, 2005

310 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

OptiX: a general purpose ray tracing engine (2010, background): “Subsequent improvements in acceleration structures [Goldsmith and Salmon 1987; MacDonald and Booth 1989] and traversal techniques[Wald et al. 2001; Havran 2001; Reshetov et al. 2005; Wald et al. 2007a] enabled interactive ray tracing on desktop-class machines [Bigler et al.”
Ray Tracing on the Cell Processor (2006, background): “Ray tracing is well-known to benefit from parallelism [17] [18], and most of the more recent ray tracing algorithms are already capable of exploiting SIMD operations [30] [21] [27] [28].”
Ray tracing deformable scenes using dynamic bounding volume hierarchies (2007, methodology): “MLRT Data was not Available for Toys, Runner, or Fairy.”
Interactive k-d tree GPU raytracing (2007, background): “Ad-ditionally, further optimizations such as frustum culling even save ray-triangle intersections and become possible when us-ing packets [Reshetov et al. 2005].”
Embree (2014, methodology): “For example, multi-frusta methods trace a frustum per lane, and each frustum is a proxy for a set of rays bounded by the frustum volume [Reshetov et al. 2005; Benthin and Wald 2009].”
Understanding the efficiency of ray traversal on GPUs (2009, methodology): “Hierarchical traversal In a coherent setting, truly impressive performance improvements have been reported on CPUs using hierarchical traversal methods (e.g. [Reshetov et al. 2005; Wald et al. 2007]).”