Presentation

<
Deformable Beta Splatting
SessionSplatting Bigger, Faster, and Adaptive
DescriptionDeformable Beta Splatting (DBS) is a novel approach for real-time radiance field rendering that leverages deformable Beta Kernels with adaptive frequency control for both geometry and color encoding. DBS captures complex geometries and lighting with state-of-the-art fidelity, while only using 45% fewer parameters and rendering 1.5x faster than 3DGS-MCMC.
Authors
Rong Liu
USC Institute for Creative Technologies (ICT)
Dylan Sun
University of Southern California
Meida Chen
USC Institute for Creative Technologies (ICT)
Yue Wang
University of Southern California
Andrew Feng
USC Institute for Creative Technologies (ICT)
Event Type
Technical Paper
TimeWednesday, 13 August 202511:35am - 11:45am PDT
LocationWest Building, Rooms 301-305
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 202510:45am - 12:35pm PDTWest Building, Rooms 301-305
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationImage-GS: Content-Adaptive Image Representation via 2D Gaussians
Similar Presentations
Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering
Quadric-Based Silhouette Sampling for Differentiable Rendering