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

<img Width="625" Height="381" Src="https://free... -

: This sets the vertical size of the image to 381 pixels. Why These Attributes Matter

For more detailed guides on image attributes, you can visit resources like the W3Schools img width documentation or the MDN Web Docs on image elements .

: You can use these attributes to force an image to display at a size different from its original file dimensions, though resizing via a program is often better for performance. <img width="625" height="381" src="https://free...

: The "source" attribute, which points to the URL or file path of the image you want to display.

Explicitly setting the width and height in your HTML is a best practice for a few reasons: : This sets the vertical size of the image to 381 pixels

The HTML code snippet you provided is used to embed an image into a webpage with a specific width and height. Breakdown of the Code Components : The HTML tag used to embed an image on a page.

: It allows the browser to reserve the exact space for the image before it even finishes downloading, preventing the page layout from jumping around as it loads. : The "source" attribute, which points to the

: This sets the horizontal size of the image to 625 pixels.

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