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

Ice_mc_scream_dj_ramezz_remix_2021 Instant

The success of the 2021 version led to subsequent updates, including a 2024 Euro Twice Refresh . Content and Composition

Popular uploads of this specific remix have amassed millions of views, with one version surpassing 2.5 million views .

The remix became a staple for "Shuffle Dance" and "Cutting Shapes" videos on YouTube and TikTok.

Featured heavily on the Kanal Djordan YouTube channel.

The remix retains Ice MC’s signature ragga-style rap and the high-pitched female vocal chorus that defined the original track's energy.


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

The success of the 2021 version led to subsequent updates, including a 2024 Euro Twice Refresh . Content and Composition

Popular uploads of this specific remix have amassed millions of views, with one version surpassing 2.5 million views .

The remix became a staple for "Shuffle Dance" and "Cutting Shapes" videos on YouTube and TikTok.

Featured heavily on the Kanal Djordan YouTube channel.

The remix retains Ice MC’s signature ragga-style rap and the high-pitched female vocal chorus that defined the original track's energy.


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