SGAD-SLAM：调整深度的点云溅射以改进RGBD SLAM中的光场
SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
AI总结：
SGAD-SLAM通过调整深度的点云溅射方法改进RGBD SLAM中的光场表示，解决传统高斯点云灵活性和运动限制的问题，提升渲染质量和跟踪效率。
摘要：
3D高斯溅射（3DGS）在RGBD SLAM中取得了显著进展。当前方法通常使用3D高斯或视图绑定的3D高斯来表示跟踪和建图中的光场。然而，这些高斯点要么过于灵活，要么运动受限，导致收敛缓慢或渲染质量有限。为了解决这个问题，我们采用像素对齐的高斯点，但允许每个高斯点沿其光线调整位置以最大化渲染质量，即使高斯点被简化以提高系统可扩展性。为了加快跟踪速度，我们将每个像素周围的深度分布建模为高斯分布，然后利用这些分布快速对每个帧进行对齐。我们在广泛使用的基准上报告了我们的评估，验证了我们的设计，并在视图渲染、相机跟踪、运行时间和存储复杂性方面优于最新方法。请参见我们的项目页面获取代码和视频：https://machineperceptionlab.github.io/SGAD-SLAM-Project。
英文摘要：
3D Gaussian Splatting (3DGS) has made remarkable progress in RGBD SLAM. Current methods usually use 3D Gaussians or view-tied 3D Gaussians to represent radiance fields in tracking and mapping. However, these Gaussians are either too flexible or too limited in movements, resulting in slow convergence or limited rendering quality. To resolve this issue, we adopt pixel-aligned Gaussians but allow each Gaussian to adjust its position along its ray to maximize the rendering quality, even if Gaussians are simplified to improve system scalability. To speed up the tracking, we model the depth distribution around each pixel as a Gaussian distribution, and then use these distributions to align each frame to the 3D scene quickly. We report our evaluations on widely used benchmarks, justify our designs, and show advantages over the latest methods in view rendering, camera tracking, runtime, and storage complexity. Please see our project page for code and videos at https://machineperceptionlab.github.io/SGAD-SLAM-Project .
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。
