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

Trackaholics Gtr2 Link

Some tracks require NoCD or 4GB patch to avoid memory crashes.

The biggest frustration with random track mods is that the AI cars drive into walls at Turn 1. Trackaholics dedicates 50% of their development time to editing files. In a Trackaholics GTR2 track, the AI brakes at the correct late apexes, overtakes in realistic zones, and even avoids you if you spin. This is what separates them from amateur modders. trackaholics gtr2

standing as a pillar of that ecosystem. While GTR2 arrived in 2006 as a masterclass in simulation, it was the relentless output of groups like Trackaholics that transformed it from a static title into a perpetual racing platform. The Community Engine Trackaholics, led by figures like SIDstalker Some tracks require NoCD or 4GB patch to

: Infusing nimble, classic touring and rally handling into a road course environment. In a Trackaholics GTR2 track, the AI brakes

Trackaholics GTR2, Trackaholics GTR2 mod, GTR2 Trackaholics pack, Trackaholics tracks, Trackaholics GTR2 power pack, GTR2 modding 2026.

For nearly two decades, Trackaholics has provided the content necessary to keep GTR2 at the forefront of sim racing, even when compared to modern titles. By focusing on quality over quantity, they have ensured that GTR2 remains a visually relevant and highly enjoyable simulation experience.

The group’s vehicle roster is equally impressive, covering everything from modern prototypes to classic touring cars.

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