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

[s1e4] What If... Doctor Strange Lost His Heart... -

In the fourth episode of What If…? , "What If... Doctor Strange Lost His Heart Instead of His Hands?", the MCU follows a tragic storyline where Doctor Strange's grief leads to the annihilation of his universe. Driven by the loss of Christine Palmer, Strange Supreme defies the Ancient One to reverse an "Absolute Point" in time, resulting in the destruction of his reality. Critical reviews labeled the episode a standout entry for its dark narrative and exploration of grief. Read the full recap at ComicsBeat .

What If...Doctor Strange Lost His Heart Instead of His Hands?

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

In the fourth episode of What If…? , "What If... Doctor Strange Lost His Heart Instead of His Hands?", the MCU follows a tragic storyline where Doctor Strange's grief leads to the annihilation of his universe. Driven by the loss of Christine Palmer, Strange Supreme defies the Ancient One to reverse an "Absolute Point" in time, resulting in the destruction of his reality. Critical reviews labeled the episode a standout entry for its dark narrative and exploration of grief. Read the full recap at ComicsBeat .

What If...Doctor Strange Lost His Heart Instead of His Hands?

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