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

Bt2016r43127ultscexe - 2021

I need to verify if this is related to a known software. Searching for similar filenames might help. However, as an AI, I can't browse the internet, so I have to rely on my training data. I recall that some games or tools use such alphanumeric strings in their executable files. For example, games like Batman: Arkham Knight might have modded versions with such filenames. Alternatively, it could be a tool or mod for a game, but without more context, it's speculative.


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

I need to verify if this is related to a known software. Searching for similar filenames might help. However, as an AI, I can't browse the internet, so I have to rely on my training data. I recall that some games or tools use such alphanumeric strings in their executable files. For example, games like Batman: Arkham Knight might have modded versions with such filenames. Alternatively, it could be a tool or mod for a game, but without more context, it's speculative.


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