Presentation
Emerging Technologies Demo - A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
DescriptionThis Emerging Technologies demo is a partner presentation to the Technical Paper:
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
Gaussian Splatting struggles with large scenes due to memory limits and chunking artifacts. We introduce "A LoD of Gaussians," a new framework enabling ultra-large scene training and rendering on a single consumer GPU. Through out-of-core streaming and Level-of-Detail, it achieves seamless multi-scale reconstruction without relying on scene partitioning.
Paper Presentation Presented: Monday, July 20, 2-3:30 pm; Paper Session: 3D Gaussian Splatting I; Room 408 A
A LoD of Gaussians: Out-of-Core Training and Rendering for Seamless Ultra-Large Scene Reconstruction
Gaussian Splatting struggles with large scenes due to memory limits and chunking artifacts. We introduce "A LoD of Gaussians," a new framework enabling ultra-large scene training and rendering on a single consumer GPU. Through out-of-core streaming and Level-of-Detail, it achieves seamless multi-scale reconstruction without relying on scene partitioning.
Paper Presentation Presented: Monday, July 20, 2-3:30 pm; Paper Session: 3D Gaussian Splatting I; Room 408 A
Event Type
Emerging Technologies
Technical Paper
TimeTuesday, 21 July 20262:40pm - 3:40pm PDT
LocationConcourse Hall
Full Conference Supporter
Full Conference
Experience
