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

The Other Guys -

In addition to these groups, there are many other examples of The Other Guys who work tirelessly behind the scenes to keep our communities running smoothly. From sanitation workers and maintenance staff, to social workers and counselors, there are countless individuals who dedicate their careers to helping others.

These individuals are often overlooked and underappreciated, but they are the backbone of our society. They are The Other Guys, working behind the scenes to keep our communities safe, healthy, and thriving. They deserve our recognition and gratitude, and we should do more to support and appreciate them. The Other Guys

Healthcare workers are another group of The Other Guys who deserve our recognition and gratitude. Doctors, nurses, and other medical professionals work tirelessly to care for the sick and injured, often in difficult and stressful conditions. They are the ones who work long hours, often for little sleep or rest, to ensure that we receive the medical care we need. In addition to these groups, there are many

Another group of The Other Guys are teachers. Teachers are often seen as authority figures, but they are so much more than that. They are mentors, role models, and friends to their students, working tirelessly to help them learn and grow. They spend countless hours grading papers, preparing lessons, and supporting their students, often without receiving the recognition they deserve. They are The Other Guys, working behind the

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