Gaussian-SLAM：基于Gaussian Splatting的逼真稠密SLAM
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
AI总结：
提出基于3D Gaussians的稠密SLAM方法，通过子地图独立优化与帧到模型相机追踪，实现可扩展的交互式重建与逼真渲染，性能优于现有神经稠密SLAM方法。
摘要：
我们提出了一种稠密同步定位与建图（SLAM）方法，使用3D Gaussians作为场景表示。该方法支持从真实世界单目RGBD视频中实现交互式时间的重建和逼真渲染。为此，我们提出了一种新颖有效的策略，为新探索区域播种新的Gaussians，并进行独立于场景规模的在线优化，从而可扩展到更大场景。这是通过将场景组织为独立优化且无需保留在内存中的子地图来实现的。我们进一步通过最小化输入帧与渲染帧之间的光度与几何损失，实现了帧到模型的相机追踪。Gaussian表示允许对真实世界场景进行高质量逼真实时渲染。在合成和真实世界数据集上的评估表明，与现有神经稠密SLAM方法相比，在地图构建、追踪和渲染方面具有竞争力或更优的性能。
英文摘要：
We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods.
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。
