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

Modern Family 4 16 Link -

barters the blame to Luke in exchange for forging a signature on a failed school project.

(played by Maxwell Caulfield), but things get awkward when Phil surprises her by showing up anyway. The "Plan Bieber" Incident

Modern Family's "Pest Control" is a shining example of how television can be used to spark meaningful conversations and challenge societal norms. As we look back on this episode, we're reminded of the power of storytelling and the importance of representation on television. If you haven't seen this episode, do yourself a favor and watch it - it's a wild ride full of laughs, love, and self-discovery.


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

barters the blame to Luke in exchange for forging a signature on a failed school project.

(played by Maxwell Caulfield), but things get awkward when Phil surprises her by showing up anyway. The "Plan Bieber" Incident

Modern Family's "Pest Control" is a shining example of how television can be used to spark meaningful conversations and challenge societal norms. As we look back on this episode, we're reminded of the power of storytelling and the importance of representation on television. If you haven't seen this episode, do yourself a favor and watch it - it's a wild ride full of laughs, love, and self-discovery.


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