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

I-land 2 Ep 1 ((free)) Jun 2026

Fuko showed solid charisma, but the team struggled with overall cohesion. "Unforgiven" (LE SSERAFIM) Ryu Sarang

Here’s a short creative piece—written as a kind of poetic recap / inner monologue—inspired by the first episode of I-LAND 2 .

were voted into I-LAND by the producers. However, because the facility only accommodates 12, the contestants had to hold an internal vote to "exile" four members to the Ground. This established the "i-mate" (fan) engagement and the cutthroat interpersonal dynamics early on. Viewing and Community i-land 2 ep 1

, a highly anticipated former R-U-Next? finalist, entered with massive fan support and demonstrated mature stage presence. She alongside Koko advanced straight to I-LAND. The First Cliffhanger: The 12-Seat Dilemma

of THEBLACKLABEL. The first episode, titled "The Beginning," introduced the 24 contestants and the new high-stakes voting and evaluation system. Key Premise and Structure Contestants and Concept Fuko showed solid charisma, but the team struggled

: Celebrated street dance choreographers who demand absolute synchronization, sharp execution, and high energy.

: A minimalist, stark training area with no individual rooms or luxury amenities. Contestants sent to the Ground face immediate elimination risk and must work twice as hard to ascend. However, because the facility only accommodates 12, the

: Since 16 contestants passed the entrance test but only 12 spots existed in I-LAND, the trainees had to vote among themselves to expel four members.

The episode centered on the "Entrance Test," where units performed to earn a spot in I-LAND. A score of at least 3 "I" votes from the 5 judges was required to pass. Key Trainees Outcome/Highlights "Drama" (aespa) Choi Jungeun Bang Jeemin Yoon Jiyoon

You can find the full episode and discussions on the following platforms: : Full episodes are available on Rakuten Viki Community Discussion : Fans track trainee updates and rankings on the

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