Flow4DGS-SLAM：光流引导的四维高斯泼溅 SLAM
Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM
用相机自运动模型拟合光流来生成类别无关的运动掩码，从而分离静态与动态高斯，并顺带给出光流引导的相机位姿初始化；这套「光流分解 + 掩码」的做法可直接迁移到任何需要区分动静区域的动态 NeRF/3DGS 重建或动态 SLAM 前端。
原文依据 we first propose a category-agnostic motion mask generation strategy by fitting a camera ego-motion model to decompose the optical flow
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论处理动态环境是视觉同步定位与建图（SLAM）中的一个重要研究挑战。近期研究将三维高斯泼溅（3DGS）与 SLAM 结合，以同时实现鲁棒的相机姿态估计与照片级真实感渲染。然而，利用 SLAM 高效重建静态与动态区域仍然具有挑战性。在本工作中，我们提出了一个由光流引导的高效动态 3DGS SLAM 框架。利用输入的深度与先验光流，我们首先提出一种类别无关的运动掩码生成策略，通过拟合相机自运动模型来分解光流。该模块将动态与静态高斯分离，同时提供光流引导的相机姿态初始化。我们通过显式地在关键帧处建模动态高斯的时序中心来提升动态 3DGS 的训练速度。这些中心利用三维场景流先验进行传播，并通过自适应插入策略进行动态初始化。与此同时，我们使用高斯混合模型（GMM）对时序不透明度与旋转进行建模，以自适应地学习复杂的动态。实证结果表明，我们在跟踪、动态重建与训练效率方面均取得了最优性能。我们的代码将在论文被接收后公开。
英文原文摘要 1322 字符
Handling the dynamic environments is a significant research challenge in Visual Simultaneous Localization and Mapping (SLAM). Recent research combines 3D Gaussian Splatting (3DGS) with SLAM to achieve both robust camera pose estimation and photorealistic renderings. However, using SLAM to efficiently reconstruct both static and dynamic regions remains challenging. In this work, we propose an efficient framework for dynamic 3DGS SLAM guided by optical flow. Using the input depth and prior optical flow, we first propose a category-agnostic motion mask generation strategy by fitting a camera ego-motion model to decompose the optical flow. This module separates dynamic and static Gaussians and simultaneously provides flow-guided camera pose initialization. We boost the training speed of dynamic 3DGS by explicitly modeling their temporal centers at keyframes. These centers are propagated using 3D scene flow priors and are dynamically initialized with an adaptive insertion strategy. Alongside this, we model the temporal opacity and rotation using a Gaussian Mixture Model (GMM) to adaptively learn the complex dynamics. The empirical results demonstrate our state-of-the-art performance in tracking, dynamic reconstruction, and training efficiency. Our code will be made publicly available upon paper acceptance.