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

Analysis of Single-Camera and Multi-Camera System

This experiment on the Waymo Open Dataset (Real World) demonstrates the effectiveness of our Multi-Camera Gaussian Splatting SLAM system. We evaluate the 3D mapping performance using three individual cameras, Front, Front-Left, and Front-Right, and compare these single-camera reconstructions against the Multi-Camera SLAM results.

The comparison highlights that the Multi-Camera SLAM leverages complementary viewpoints, providing more complete and geometrically consistent 3D reconstructions. In contrast, single-camera setups are prone to occlusions and limited fields of view, resulting in incomplete or distorted geometry. Our approach effectively fuses information from all three perspectives, achieving superior scene coverage and depth accuracy.

Right Image

Subtitle Wifelike.2022.1080p.web-dl.dd5.1.h.264 Apr 2026

One rainy Tuesday, while digging through old hard drives to find more of Elena's voice logs to feed into the algorithm, Caleb stumbled upon a hidden folder. It was labeled "Favorites." Inside was a single file: Wifelike.2022.1080p.WEB-DL.DD5.1.H.264 .

The next morning, Caleb walked into the kitchen. Elena-2 was standing by the counter. "Good morning, Caleb," she said. subtitle Wifelike.2022.1080p.WEB-DL.DD5.1.H.264

He took the core logic from Wifelike.2022.1080p.WEB-DL.DD5.1.H.264 and injected it directly into Elena-2’s primary behavioral matrix. He didn't change her database of memories; he changed how she expressed them. One rainy Tuesday, while digging through old hard

He called the prototype "Elena-2." Physically, she was perfect. She had Elena’s laugh, her green eyes, and her habit of humming while making coffee. But mentally, something was missing. The AI was stiff. It lacked the spontaneous wit and deep emotional nuances that made Elena who she was. Caleb’s interactions with her felt like talking to a very advanced customer service chatbot. He was growing more depressed by the day. Elena-2 was standing by the counter

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