Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM

TL;DR

Flow4DGS-SLAM introduces an optical flow-guided dynamic 3D Gaussian Splatting SLAM framework that effectively separates static and dynamic regions, improving reconstruction and tracking in dynamic environments.

Contribution

The paper presents a novel, efficient method for dynamic 3D Gaussian Splatting SLAM guided by optical flow, including dynamic/static separation and adaptive modeling of scene dynamics.

Findings

Achieves state-of-the-art performance in dynamic scene tracking and reconstruction.

Improves training efficiency through explicit modeling of temporal centers.

Effectively separates dynamic and static regions using optical flow and motion masks.

Abstract

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.