GRay: Ray Tracing 3D Gaussians Near the Speed of Splats
For researchers in radiance field reconstruction, GRay provides a ray tracing alternative that matches the speed of rasterization-based 3DGS, enabling efficient rendering of dense scenes with many tiny Gaussians.
GRay is a fast ray tracer for 3D Gaussians that closes the performance gap with 3DGS, achieving nearly 4x faster rendering and 10x faster optimization than 3DGRT while maintaining similar quality, and competitive speed with 3DGS at somewhat lower quality.
3D Gaussian Splatting (3DGS) is a popular representation for radiance field reconstruction, distinguished by the rendering speed of its rasterization-based renderer. While 3D Gaussians can also be ray traced, this approach has so far been slower, with 3D Gaussian Ray Tracing (3DGRT) taking nearly one order of magnitude longer to optimize. To address this, we present GRay, a fast ray tracer for 3D Gaussians designed to close this performance gap and match 3DGS's speed. Our method leverages the algorithmic difference between both approaches: unlike rasterization, ray tracing evaluates only Gaussians that are actually intersected by a ray, leading to potentially logarithmic--rather than linear--scaling in the number of primitives. This property allows ray tracing to better exploit dense scenes composed of numerous tiny Gaussians, a configuration which has largely been overlooked. Notably, we show that dense initialization--which creates many small Gaussians--slows down rasterization, but instead speeds up ray tracing. Designed to leverage this effect, GRay renders nearly 4x faster and optimizes nearly 10x faster than 3DGRT while maintaining similar quality, and has competitive speed with 3DGS albeit at somewhat lower quality. Code is available at https://repo-sam.inria.fr/nerphys/gray.