Raytracing Dynamic Scenes on the GPU Using Grids

Abstract

Abstract-Raytracing dynamic scenes at interactive rates have received a lot of attention recently. We present a few strategies for high performance raytracing on a commodity GPU. The construction of grids needs sorting, which is fast on today's GPUs. The grid is thus the acceleration structure of choice for dynamic scenes as per-frame rebuilding is required. We advocate the use of appropriate data structures for each stage of raytracing, resulting in multiple structure building per frame. A perspective grid built for the camera achieves perfect coherence for primary rays. A perspective grid built with respect to each light source provides the best performance for shadow rays. Spherical grids handle lights positioned inside the model space and handle spotlights. Uniform grids are best for reflection and refraction rays with little coherence. We propose an Enforced Coherence method to bring coherence to them by rearranging the ray to voxel mapping using sorting. This gives the best performance on GPUs with only user-managed caches. We also propose a simple, Independent Voxel Walk method, which performs best by taking advantage of the L1 and L2 caches on recent GPUs. We achieve over 10 fps of total rendering on the Conference model with one light source and one reflection bounce, while rebuilding the data structure for each stage. Ideas presented here are likely to give high performance on the future GPUs as well as other manycore architectures.

Adaptive Raytracing Implementation Using Partial Dynamic Reconfiguration

“…The literature proposes works focusing on Grids [16], Bounding Volume Hierarchies (BHV) [17] and KD-Trees [18]. However, there is not an optimal data structure to represent the input scene, but this depends on the computing platform adopted for the implementation of the algorithm.…”

Divide and Conquer Ray Tracing Algorithm Based on BVH Partition

“…Zhou [15] greatly improved ray tracing by implementing Kdtree building on GPU. And also Perrotte [16] and Guntury [17] implemented Grids building under the perspective view and ray tracing with Grids on GPU.…”

Efficient Illumination Algorithms for Global Illumination In Interactive and Real-Time Rendering

“…By using geometric primitives instead of sampled fragment data, analytic tests can be performed, resulting in accurate image generation. Similar to Guntury et al [GN12], we also exploit per-view perspective grids. However in our case, cells are irregularly sized in the depth dimension, based on the pixel's depth bounds, and hierarchically organized in the image domain, enabling early space skipping that significantly improves traversal in arbitrary environments.…”

“…However, traversal performance in environments containing moderately non-uniform geometry distribution can be increased by employing a two-level level adaptive subdivision [KBS11]. Finally, the use of perspective grids, i.e., a perspective regular subdivision with respect to a particular viewpoint (right of Figure 3.1), can improve coherence on primary as well as on shadow rays [GN12].…”

“…Uniform grids, on the other hand, are able to maintain fast construction times, but traversal performs poorly even for primary rays in environments with non-uniform distribution of primitives as they cannot exploit empty space skipping. Primary ray performance, however, can be mitigated by employing more elaborate schemes, such as perspective grids [GN12].…”