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

Looking At Me (feat. Jwavywtt) Site

The track features (Josiah Lewiel), an emerging artist known for a style that fans frequently compare to NBA YoungBoy due to his melodic delivery and raw lyrical themes. Jwavywtt has built a significant presence through platforms like Spotify and Instagram , where he often shares singles that blend gritty street narratives with emotional vulnerability. His involvement in the "Wavytheteam" (WTT) collective further establishes his place within a community of artists pushing a distinct "wavy" sound. Musical Style

A blend of rhythmic flows and sung choruses, similar to the "lightskin YB" style attributed to him by listeners. Looking at me (feat. Jwavywtt)

Common themes in Jwavywtt’s discography include self-reflection, navigating personal struggles, and the pressures of newfound attention (as suggested by the title "Looking at Me"). Context The track features (Josiah Lewiel), an emerging artist

"Looking at Me (feat. Jwavywtt)" is a contemporary track that highlights the collaborative energy between rising artists in the modern hip-hop and R&B scene. Musical Style A blend of rhythmic flows and

Jwavywtt has been prolific in recent years, releasing albums such as Back From The Dead (2024) and All Eyes On Me (2025). Collaborations like "Looking at Me" serve to bridge different fanbases within the underground rap scene, often premiered through platforms like SoundCloud or showcased via reels on his Instagram . Josiah Lewiel (@jwavywtt) • Instagram photos and videos

Based on the collaboration and Jwavywtt's previous work, the song likely features:

Expect heavy bass, atmospheric synthesizers, and the polished "new wave" rap aesthetic found in recent projects like his 2025 album All Eyes On Me .

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