MCGS-SLAM

A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping

Anonymous Author
Code and data [Available Upon Acceptance]

SLAM System Pipeline

Our method performs real-time SLAM by fusing synchronized inputs from a multi-camera rig into a unified 3D Gaussian map. It first selects keyframes and estimates depth and normal maps for each camera, then jointly optimizes poses and depths via multi-camera bundle adjustment and scale-consistent depth alignment. Refined keyframes are fused into a dense Gaussian map using differentiable rasterization, interleaved with densification and pruning. An optional offline stage further refines camera trajectories and map quality. The system supports RGB inputs, enabling accurate tracking and photorealistic reconstruction.

Right Image

Analysis of Single-Camera and Multi-Camera System

This experiment on the Waymo Open Dataset (Real World) demonstrates the effectiveness of our Multi-Camera Gaussian Splatting SLAM system. We evaluate the 3D mapping performance using three individual cameras, Front, Front-Left, and Front-Right, and compare these single-camera reconstructions against the Multi-Camera SLAM results.

The comparison highlights that the Multi-Camera SLAM leverages complementary viewpoints, providing more complete and geometrically consistent 3D reconstructions. In contrast, single-camera setups are prone to occlusions and limited fields of view, resulting in incomplete or distorted geometry. Our approach effectively fuses information from all three perspectives, achieving superior scene coverage and depth accuracy.

Right Image

Sam_singhal_28_aprmp4

: His production credits include high-profile programs such as NBC Nightly News with Tom Llamas , Dateline NBC , and NBC News Decision 2010 .

Sam Singal is a veteran television and digital news producer with extensive experience in the news industry. He is currently the at Spectrum Networks , where he oversees content creation and editorial development for their platforms. Career Highlights Sam_Singhal_28_Aprmp4

: In 2020, Singal was named Vice President of Content and Editorial to lead the launch of a new, innovative mobile news app designed for Spectrum subscribers. : His production credits include high-profile programs such

: Before joining Spectrum, he served as an Executive Producer at NBC News. Career Highlights : In 2020, Singal was named

: Throughout his career, he has earned a total of 3 wins and 17 nominations for various media awards. Leadership & Vision

Singal's role at Spectrum was specifically created to address the evolving ways customers access local news across different devices. He is recognized for his ability to lead the production of "award-winning news content" and his expertise in the digital news space.

Analysis of Single-Camera and Multi-Camera SLAM (Tracking)

In this section, we benchmark tracking accuracy across eight driving sequences from the Waymo dataset (Real World). MCGS-SLAM achieves the lowest average ATE, significantly outperforming single-camera methods.
Right Image

We further evaluate tracking on four sequences from the Oxford Spires dataset (Real World). MCGS-SLAM consistently yields the best performance, demonstrating robust trajectory estimation in large-scale outdoor environments.
Right Image

Right Image