CL-Splats：基于局部优化的高斯泼溅持续学习
CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization
AI总结：
CL-Splats提出一种基于局部优化的高斯泼溅持续学习方法，通过变更检测实现高效增量更新，提升重建质量，支持场景状态存储与恢复。
摘要：
在动态3D环境中，随时间准确更新场景表示对于机器人、混合现实和具身智能等应用至关重要。随着场景的演变，需要高效的方法来纳入变化，以维持最新、高质量的重建，同时避免重新优化整个场景的计算开销。本文介绍了CL-Splats，它从稀疏场景捕获中增量更新基于高斯泼溅的3D表示。CL-Splats集成了一个鲁棒的变更检测模块，该模块分割场景中的更新和静态组件，从而实现聚焦的局部优化，避免不必要的重新计算。此外，CL-Splats支持存储和恢复先前的场景状态，促进时间分割和新的场景分析应用。我们的大量实验表明，CL-Splats实现了高效更新，且重建质量优于现有技术水平。这为未来3D场景重建任务中的实时适应奠定了坚实基础。
英文摘要：
In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
