MCGS-SLAM

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

Anonymous Author

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

Melissa Jane - Xo.pdf -

📌 : If you are searching for an ARC (Advanced Reader Copy), these were previously distributed in formats like EPUB and PDF through specific sign-up forms during the book's 2019 launch period.

: The story follows the character Jacob Lynch and features an "arrogant, smug" protagonist typical of the genre. Where to Find It

If you are looking for the text, you can find her work on official platforms: : View her full Author Profile and Book List .

: She is active as @melissajaneauthor on Instagram.

: Her books are typically available on Amazon and other major ebook retailers.


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

📌 : If you are searching for an ARC (Advanced Reader Copy), these were previously distributed in formats like EPUB and PDF through specific sign-up forms during the book's 2019 launch period.

: The story follows the character Jacob Lynch and features an "arrogant, smug" protagonist typical of the genre. Where to Find It

If you are looking for the text, you can find her work on official platforms: : View her full Author Profile and Book List .

: She is active as @melissajaneauthor on Instagram.

: Her books are typically available on Amazon and other major ebook retailers.


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