Year: 2025
Type: conference-paper
Abstract: D Gaussian Splatting (3DGS) has significantly improved the efficiency and realism of three-dimensional scene visualization in several applications, ranging from robotics to eXtended Reality (XR). This work presents SAGE (Semantic-Driven Adaptive Gaussian Splatting in Extended Reality), a novel framework designed to enhance the user experience by dynamically adapting the Level of Detail (LOD) of different 3DGS objects identified via semantic segmentation. Experimental results demonstrate how SAGE effectively reduces memory and computational overhead while keeping a desired target visual quality, thus providing a powerful optimization for interactive XR applications.
Institution: University of Padua
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417052383