3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
Nicolas Moenne-Loccoz, Ashkan Mirzaei, Or Perel, Riccardo de Lutio,, Janick Martinez Esturo, Gavriel State, Sanja Fidler, Nicholas Sharp, Zan, Gojcic

TL;DR
This paper introduces a fast GPU-based ray tracing method for particle scenes represented by 3D Gaussian splatting, enabling efficient rendering with improved accuracy and flexibility over traditional rasterization techniques.
Contribution
It presents a novel GPU-accelerated ray tracing algorithm for particle scenes, utilizing bounding volume hierarchies and specialized intersection methods to enhance rendering performance and capabilities.
Findings
Demonstrates significant speed improvements over rasterization methods
Achieves high accuracy in rendering complex particle scenes
Enables advanced effects like shadows and reflections in particle rendering
Abstract
Particle-based representations of radiance fields such as 3D Gaussian Splatting have found great success for reconstructing and re-rendering of complex scenes. Most existing methods render particles via rasterization, projecting them to screen space tiles for processing in a sorted order. This work instead considers ray tracing the particles, building a bounding volume hierarchy and casting a ray for each pixel using high-performance GPU ray tracing hardware. To efficiently handle large numbers of semi-transparent particles, we describe a specialized rendering algorithm which encapsulates particles with bounding meshes to leverage fast ray-triangle intersections, and shades batches of intersections in depth-order. The benefits of ray tracing are well-known in computer graphics: processing incoherent rays for secondary lighting effects such as shadows and reflections, rendering from…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMedical Image Segmentation Techniques · Computer Graphics and Visualization Techniques · AI in cancer detection
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
