SDGS：空间差分引导的高斯泼溅用于同时定位与三维重建
SDGS: Spatial Difference Guided Gaussian Splatting for Simultaneous Localization and 3D Reconstruction
用边缘对齐的稀疏高斯地图配合距离变换目标做 6-DoF 位姿估计，把渲染对齐从稠密光度误差换成稀疏边缘误差，单次迭代位姿优化约快 2 倍；同时引入输出空间差分边缘信号的双通道混合像素传感器，为高速运动下的跟踪与去模糊重建提供可直接复用的监督信号。
原文依据 estimates 6-DoF camera poses by aligning rendered 3D edges with observed 2D edges using a distance transform based objective
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）近来已成为一种强大的显式三维表示，能够实现照片级真实感与实时的全新视角合成。然而，大多数 3DGS 流程仍假设相机位姿已预先计算并采用离线优化，这引入了延迟，并使其在快速运动的真实场景中十分脆弱。现有的在线 3DGS 系统大多分为两类：（1）依赖独立的传统 SLAM 系统提供相机位姿、并将高斯优化与跟踪解耦的混合系统，这增加了系统复杂度；（2）纯高斯系统，其从稠密光度误差中估计位姿，需要反复渲染大量高斯，因而带来高昂的计算开销。此外，当前的在线方法往往对运动模糊和高动态范围场景敏感，限制了其在实际中的应用。我们用一个稀疏的、边缘引导的在线 3DGS 框架来解决这些局限。本方法将场景表示为边缘对齐的稀疏高斯地图，并利用基于距离变换的目标函数，将渲染得到的三维边缘与观测到的二维边缘对齐，从而估计 6 自由度相机位姿，使每次迭代的位姿优化比现有基于高斯的系统快约 2 倍，同时恢复出清晰的场景几何。我们进一步利用一种双通道混合像素视觉传感器，它在输出 RGB 图像的同时输出无模糊、高帧率的空间差分边缘信号，并将这些信号同时用于鲁棒的基于边缘的跟踪，以及一种缓解稠密三维重建中运动模糊的相互监督方案。本系统在极高速度运动下——现有仅依赖 RGB 的方法会失效的场景中——仍能保持稳定的跟踪与高保真几何，同时兼容标准 RGB 相机，并达到有竞争力的跟踪精度。
英文原文摘要 1837 字符
3D Gaussian Splatting (3DGS) has recently emerged as a powerful explicit 3D representation, enabling photorealistic and real-time novel view synthesis. However, most 3DGS pipelines still assume precomputed camera poses and offline optimization, which introduces latency and makes them brittle in fast-motion, real-world scenarios. Existing online 3DGS systems mostly fall into two camps: (1) hybrid systems that rely on a separate traditional SLAM system for camera poses and optimize Gaussians decoupled from tracking, increasing system complexity; and (2) purely Gaussian-based systems that estimate poses from dense photometric errors, requiring repeated rendering of a large number of Gaussians and thus incurring high computational cost. Moreover, current online methods are often sensitive to motion blur and high dynamic range scenes, limiting their applicability in practice.We address these limitations with a sparse, edge-guided online 3DGS framework. Our method represents the scene as an edge-aligned sparse Gaussian map and estimates 6-DoF camera poses by aligning rendered 3D edges with observed 2D edges using a distance transform based objective, yielding roughly 2x faster per-iteration pose optimization than existing Gaussian-based systems while recovering clear scene geometry. We further leverage a dual-channel hybrid pixel vision sensor that outputs blur-free, high-frame-rate spatial-difference edge signals alongside RGB images, and use these signals both for robust edge-based tracking and for a mutual supervision scheme that mitigates motion blur in dense 3D reconstruction. Our system maintains stable tracking and high-fidelity geometry under extremely high-speed motion, where existing RGB-only methods fail, while remaining compatible with standard RGB cameras and achieving competitive tracking accuracy.