SAGE通过语义驱动自适应调整3D高斯点云细节，提升扩展现实交互体验
SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality
- 根据语义分割动态调节3D高斯点云的细节层级
- 在保持目标视觉质量前提下降低内存与计算开销
- 适合对实时性要求高的扩展现实应用开发
3D高斯点云（3DGS）在机器人到扩展现实（XR）等多个领域显著提升了三维场景可视化的效率与真实感。本文提出SAGE（语义驱动的扩展现实自适应高斯点云），通过语义分割识别不同3DGS物体，并动态调整其细节层次（LOD）。实验表明，SAGE能有效降低内存与计算开销，同时维持目标视觉质量，为交互式XR应用提供强大优化方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。