Performance Comparison of Bounding Volume Hierarchies and Kd‐Trees for GPU Ray Tracing

Abstract

We present a performance comparison of bounding volume hierarchies and kd-trees for ray tracing on many-core architectures (GPUs). The comparison is focused on rendering times and traversal characteristics on the GPU using data structures that were optimized for very high performance of tracing rays. To achieve low rendering times, we extensively examine the constants used in termination criteria for the two data structures. We show that for a contemporary GPU architecture (NVIDIA Kepler) bounding volume hierarchies have higher ray tracing performance than kd-trees for simple and moderately complex scenes. On the other hand, kd-trees have higher performance for complex scenes, in particular for those with high depth complexity. Finally, we analyse the causes of the performance discrepancies using the profiling characteristics of the ray tracing kernels.

Vostok: 3D scanner simulation for industrial robot environments

“…One of the optimizations that deserves a separate discussion regards the use of voxeling [21,22]. During an iteration of the ray tracing algorithm, it is necessary to search for all the intersections between a ray and object surfaces.…”

Rectangular Selection of Components in Large 3D Models on the Web

“…There is much recent work on applying GPUs to collision detection utilising the latest shader model features or frameworks such as CUDA, often concerned with the application of acceleration structures, c.f. [Chitalu et al 2018;Dos Santos et al 2014;Vinkler et al 2016]. However, the application of GPUs to collision detection began before introduction of general purpose compute features.…”

Real-Time Collision Detection for Deformable Characters with Radial Fields

“…Many works use GPUs to accelerate BVH construction [12], [14] and traversal [53]. We base our implementation on Lauterbach et al [15] and Tang et al [16], as these are concerned with deformable objects.…”