Fast BVH Construction on GPUs

485 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.

Fast GPU-based locality sensitive hashing for k-nearest neighbor computation (2011, background): “The Morton curve can be constructed and searched eﬃciently on the GPU [27].”
OptiX: a general purpose ray tracing engine (2010, methodology): “The currently implemented acceleration structures include algorithms focused on hierarchy quality (e.g. the SBVH [Stich et al. 2009]), on construction speed (e.g. the LBVH [Lauterbach et al. 2009]), and various balance levels in between.”
Design and implementation of a parallel priority queue on many-core architectures (2012, methodology): “A number of tree-based data structures, such as R-tree [9], KDtree [10]–[12], Octree [13]–[19], decision tree [20], [21], and bounding volume hierarchy [22] have been ported to GPGPUs.”
Embree (2014, methodology): “The highest performance BVH build kernel in Embree uses Morton codes to express the construction process in terms of a simple radix sort [Lauterbach et al. 2009].”
Differentiable vector graphics rasterization for editing and learning (2020, methodology): “We sort the bounding volumes of the primitives by the 2D Morton codes of the box center [Lauterbach et al. 2009].”
Designing efficient sorting algorithms for manycore GPUs (2009, background): “The construction of spatial data structures that are essential in computer graphics and geographic information systems is fundamentally a sorting process [5], [6].”