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

All+darck+repacks+better

The Repack was a mysterious process, hidden from prying eyes. When Elian emerged, he was different. His powers were more refined, his ambition clearer. He had become Elianore, a mage of unparalleled skill and precision. The Repack had not only honed his magical prowess but had also instilled in him a sense of purpose.

As Elianore navigated this complex moral landscape, he began to unravel the mystery of The Archon's true intentions. Was the goal to create a utopia of optimized beings, or was there a more sinister purpose at play?

Elian, before the Repack, was a talented but aimless wizard, often finding himself at odds with the governing Council of Mages. His magic was potent but uncontrolled, a danger to himself and others. That was until The Archon appeared, offering Elian a chance to become "better." all+darck+repacks+better

The journey led Elianore to confront The Archon, a being capable of manipulating reality. The encounter was enlightening and terrifying. The Archon revealed a profound truth: every repack was not just about making something better but also about pushing the boundaries of what it means to be alive.

The Archon, a mysterious individual with the ability to manipulate reality on a whim, was known across the city for a singular reason: the creation of "Repacks." These were not just any repacks but comprehensive overhauls of anything - an object, a person, a concept - transforming them into something fundamentally better, yet eerily similar to their original form. The Repack was a mysterious process, hidden from prying eyes

The story of The Archon and Elianore became a cautionary tale, told across Nova Haven. It questioned the nature of self, improvement, and the price of progress. In the end, The Archon vanished as mysteriously as he appeared, leaving behind a city forever changed and a legend that would inspire generations to come.

The tale of Nova Haven and its Archon of Repackaging continued to evolve, a testament to the enduring power of stories to reflect, critique, and shape our understanding of the world. He had become Elianore, a mage of unparalleled

The story begins on a day much like any other in Nova Haven. The sun rose over the spire of the Great Library, casting a golden glow over the cobblestone streets. But amidst this serene backdrop, whispers circulated about the latest Repack. People spoke in hushed tones about a figure, once known as Elian, a skilled but struggling mage who had been repacked by The Archon.

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