Search papers, labs, and topics across Lattice.
This paper introduces GSO-SLAM, a real-time monocular SLAM system that bidirectionally couples Visual Odometry (VO) and Gaussian Splatting (GS) for simultaneous tracking and mapping. It addresses the limitations of unified or loosely integrated approaches by formulating a joint optimization within an Expectation-Maximization (EM) framework, refining VO-derived depth estimates and the GS representation concurrently. The method also introduces Gaussian Splat Initialization, leveraging image information and VO data to efficiently initialize the Gaussian scene, achieving state-of-the-art reconstruction fidelity and tracking accuracy in real-time.
Achieve state-of-the-art SLAM accuracy and real-time performance by bidirectionally coupling Visual Odometry and Gaussian Splatting within an EM framework, eliminating computational overhead.
We propose GSO-SLAM, a real-time monocular dense SLAM system that leverages Gaussian scene representation. Unlike existing methods that couple tracking and mapping with a unified scene, incurring computational costs, or loosely integrate them with well-structured tracking frameworks, introducing redundancies, our method bidirectionally couples Visual Odometry (VO) and Gaussian Splatting (GS). Specifically, our approach formulates joint optimization within an Expectation-Maximization (EM) framework, enabling the simultaneous refinement of VO-derived semi-dense depth estimates and the GS representation without additional computational overhead. Moreover, we present Gaussian Splat Initialization, which utilizes image information, keyframe poses, and pixel associations from VO to produce close approximations to the final Gaussian scene, thereby eliminating the need for heuristic methods. Through extensive experiments, we validate the effectiveness of our method, showing that it not only operates in real time but also achieves state-of-the-art geometric/photometric fidelity of the reconstructed scene and tracking accuracy.
