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

Black Lace - Busty Dusty

"Busty dusty black lace" is more than a style; it is a narrative of . It suggests a figure that has emerged from the "smoke and spices" of the past, carrying the weight of history (the dust and lace) while asserting a bold, physical presence in the now. It is the uniform of the "modern gothic"—someone who finds power in the shadows and beauty in the things others have left to gather dust. Director Series #17 Mario Bava - Facebook

: In the tradition of Italian Giallo and Gothic horror (like the works of Mario Bava ), "dusty" textures create a visceral sense of dread and nostalgia. It is the aesthetic of the "beautiful ruin," where the decay of the object enhances its allure. The Subversive "Busty" Silhouette

: Dust implies neglect, attic-bound trunks, and the passage of years. It softens the starkness of the black lace, turning a "new" garment into an "artifact." busty dusty black lace

The term "busty" introduces a modern, body-positive, and transgressive element to the traditional gothic trope.

The phrase "busty dusty black lace" serves as a striking aesthetic anchor, evoking a specific subgenre of gothic maximalism that blends vintage decay with bold, feminine silhouettes. Exploring this through a "deep essay" lens requires unweaving the three core elements—the body, the age, and the material—to understand how they construct a modern visual identity. The Materiality of Memory: Black Lace "Busty dusty black lace" is more than a

The "dusty" descriptor moves this beyond mere fashion and into the realm of the .

: By pairing a hyper-feminine, "busty" silhouette with the somber, "dusty" lace, the wearer subverts the "fragile ghost" archetype. It replaces the waifish Victorian ideal with a presence that is substantial and undeniable. Director Series #17 Mario Bava - Facebook :

Black lace is inherently paradoxical. Historically, it is the fabric of both the mourning widow and the femme fatale. As a textile, lace is defined by its "negative space"—the holes are as important as the thread. In a philosophical sense, wearing black lace is an act of wearing shadows. It suggests a history that is intricate yet fractured, a "fragmented elegance" that hides as much as it reveals. The Aesthetic of the "Dusty"

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