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

2021: Gallery+shiori+suwano+17

In a quiet town called , young artist Shiori runs a small gallery where she displays works from local creators. One day, she discovers a mysterious painting tucked away in her fatherā€™s old studio: a vibrant piece titled "17." The number 17, she learns from her late fatherā€™s journal, represents his belief that ā€œlife is built on 17 choices that shape who we become.ā€

I should check if there's actually a work named "Shiori Suwano" or similar. Searching briefly, I don't find a popular series by that name. It might be a mix of names or a misunderstanding. Alternatively, the user could be referring to "Kyoukai no Hana" by Yurika Yamajin, where Shiori is a character. The number 17 could be the volume. gallery+shiori+suwano+17

Assuming that's the case, I can craft a response discussing a specific plot point from volume 17, highlighting its significance, themes, and how it contributes to the overall narrative. Focus on making the story useful by reflecting on its lessons. If unsure, it's better to ask for clarification or mention the ambiguity. In a quiet town called , young artist

If you're looking for a idea inspired by these elements, here's a short, uplifting narrative: Title: "The Gallery of Memories" It might be a mix of names or a misunderstanding

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