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

Scgrc.7z Apr 2026

If you prefer using the terminal or command prompt, you can interact with the file using these standard commands:

It supports strong AES-256 encryption . If the "SCGRC.7z" file asks for a password, your data is highly protected.

The query "SCGRC.7z" likely refers to a compressed archive file (indicated by the extension) created using the 7-Zip archiver . The "SCGRC" portion is likely a specific project name, perhaps standing for something like "Smart City Global Research Center" or a similar academic/technical acronym. SCGRC.7z

The command-line port of 7-Zip for Linux distributions. 2. Benefits of the .7z Format

While the exact contents depend on the source of your file, here is helpful information for managing files. 1. How to Open the File If you prefer using the terminal or command

The official, free, and open-source tool. You can download it from 7-zip.org . Keka (macOS): A popular open-source option for Mac users.

It can handle archives up to 16,000,000,000 GB in size. 3. Basic Commands (Command Line) The "SCGRC" portion is likely a specific project

It typically offers 30–70% better compression than standard ZIP files, making it ideal for large backups or datasets.

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