CaRtGS：面向实时高斯泼溅SLAM的计算对齐
CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM
AI总结：
CaRtGS提出一种自适应计算对齐策略，通过增强优化迭代、解决长尾优化和改进稠密化，在实时高斯泼溅SLAM中以更少高斯基元实现高保真逼真场景重建。
摘要：
同时定位与建图（SLAM）在机器人学中至关重要，其中逼真场景重建已成为一项关键挑战。为解决这一问题，我们提出了面向实时高斯泼溅SLAM的计算对齐方法（CaRtGS），这是一种在实时环境中提升逼真场景重建效率与质量的新方法。CaRtGS利用3D高斯泼溅（3DGS），实现了卓越的渲染质量和处理速度，这对场景逼真重建至关重要。我们的方法通过一种自适应策略来解决高斯泼溅SLAM（GS-SLAM）中的计算错位问题，该策略增强了优化迭代次数、解决了长尾优化问题并改进了稠密化过程。在Replica、TUM-RGBD和VECtor数据集上的实验表明，CaRtGS能够以更少的高斯基元实现高保真渲染。这项工作推动SLAM朝着实时、逼真的稠密渲染方向发展，显著推进了逼真场景表示。为造福研究社区，我们在项目网站上公开了代码和配套视频：https://dapengfeng.github.io/cartgs。
英文摘要：
Simultaneous Localization and Mapping (SLAM) is pivotal in robotics, with photorealistic scene reconstruction emerging as a key challenge. To address this, we introduce Computational Alignment for Real-Time Gaussian Splatting SLAM (CaRtGS), a novel method enhancing the efficiency and quality of photorealistic scene reconstruction in real-time environments. Leveraging 3D Gaussian Splatting (3DGS), CaRtGS achieves superior rendering quality and processing speed, which is crucial for scene photorealistic reconstruction. Our approach tackles computational misalignment in Gaussian Splatting SLAM (GS-SLAM) through an adaptive strategy that enhances optimization iterations, addresses long-tail optimization, and refines densification. Experiments on Replica, TUM-RGBD, and VECtor datasets demonstrate CaRtGS's effectiveness in achieving high-fidelity rendering with fewer Gaussian primitives. This work propels SLAM towards real-time, photorealistic dense rendering, significantly advancing photorealistic scene representation. For the benefit of the research community, we release the code and accompanying videos on our project website: https://dapengfeng.github.io/cartgs.
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。
