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

Doctoradventures.14.04.27.connie.carter.nurse.c...: [exclusive]

Connie Carter, Nurse

As we embarked on our journey, I was struck by Dr. Carter's unwavering commitment to his patients. His kindness, empathy, and expertise inspired me to push beyond my limits and strive for excellence in my own practice. Together, we navigated the complexities of healthcare, working tirelessly to diagnose and treat a wide range of medical conditions. DoctorAdventures.14.04.27.Connie.Carter.Nurse.C...

It all began when I met Dr. Carter, a renowned doctor with a passion for delivering quality healthcare to those in need. Our collaboration was a turning point in my career, as I was tasked with assisting him on a mission to provide medical care to underserved communities. I was both excited and nervous about the challenges that lay ahead. Connie Carter, Nurse As we embarked on our

April 27, 2014

As I reflect on my journey as a nurse, I am reminded of the countless moments that have shaped me into the compassionate and dedicated healthcare professional I am today. My adventure with Dr. Carter was one such experience that has left an indelible mark on my heart. Our collaboration was a turning point in my

As I look back on my adventure with Dr. Carter, I am filled with a sense of gratitude and awe. I am grateful for the experience, the lessons learned, and the friendships forged along the way. I am in awe of the resilience and strength of the human spirit, and I am proud to be part of a community that is dedicated to healing and making a positive impact on the world.

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