迈向实时高斯泼溅：通过光度SLAM加速3DGS
Towards Real-Time Gaussian Splatting: Accelerating 3DGS through Photometric SLAM
AI总结：
本文提出将3DGS与直接稀疏里程计（DSO）这一单目光度SLAM系统集成，利用DSO点云输出替代传统运动恢复结构方法，显著缩短高质量渲染所需的训练时间，从而推动3DGS集成SLAM系统在移动硬件上实现实时运行。
摘要：
3D高斯泼溅（3DGS）在视觉同时定位与建图（VSLAM）中的初步应用展示了从单目视频流生成高质量体积重建的能力。然而，尽管取得了这些有前景的进展，当前3DGS集成方案与传统VSLAM相比，跟踪性能有所下降，运行速度也更低。为解决这些问题，我们提出将3DGS与直接稀疏里程计（Direct Sparse Odometry）这一单目光度SLAM系统相结合。我们进行的初步实验表明，与标准的运动恢复结构（structure-from-motion）方法相比，使用直接稀疏里程计的点云输出能够显著缩短实现高质量渲染所需的训练时间。缩短3DGS训练时间使得开发可在移动硬件上实时运行的3DGS集成SLAM系统成为可能。这些有前景的初步发现表明，进一步探索传统VSLAM系统与3DGS的结合是值得的。
英文摘要：
Initial applications of 3D Gaussian Splatting (3DGS) in Visual Simultaneous Localization and Mapping (VSLAM) demonstrate the generation of high-quality volumetric reconstructions from monocular video streams. However, despite these promising advancements, current 3DGS integrations have reduced tracking performance and lower operating speeds compared to traditional VSLAM. To address these issues, we propose integrating 3DGS with Direct Sparse Odometry, a monocular photometric SLAM system. We have done preliminary experiments showing that using Direct Sparse Odometry point cloud outputs, as opposed to standard structure-from-motion methods, significantly shortens the training time needed to achieve high-quality renders. Reducing 3DGS training time enables the development of 3DGS-integrated SLAM systems that operate in real-time on mobile hardware. These promising initial findings suggest further exploration is warranted in combining traditional VSLAM systems with 3DGS.
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。
