通过可调深度的高斯点优化辐射场，提升RGBD SLAM的渲染质量与追踪速度。
SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM
- 让每个高斯点沿射线调整位置以优化渲染效果。
- 用像素级深度分布加速帧对齐，提升追踪效率。
- 在渲染质量、速度和存储上优于最新方法，适合实时3D重建场景。
3D高斯点渲染（3DGS）在RGBD SLAM中取得显著进展。现有方法通常使用3D高斯或视角绑定的3D高斯表示辐射场，但其运动灵活性或受限，导致收敛慢或渲染质量差。为此，本文采用像素对齐的高斯点，并允许每个高斯点沿射线调整位置，以最大化渲染质量，同时简化结构以提升系统可扩展性。为加速追踪，我们建模每个像素周围的深度分布为高斯分布，并利用这些分布快速对齐各帧至3D场景。我们在多个常用基准上进行评估，验证设计合理性，并展示在视图渲染、相机追踪、运行时间和存储复杂度上优于最新方法。代码与视频见项目主页：https://machineperceptionlab.github.io/SGAD-SLAM-Project。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。