SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality
This work provides an incremental optimization for interactive extended reality applications, improving efficiency for users in fields like robotics and XR.
The paper tackles the problem of optimizing 3D Gaussian Splatting for extended reality by dynamically adjusting the level of detail based on semantic segmentation, resulting in reduced memory and computational overhead while maintaining target visual quality.
3D 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 a 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.