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

Choti Bachi Ki | Chudai

In this example, Aisha's actions demonstrate "choti bachi ki chudai." Her courage and determination serve as an inspiration to others, and her story is likely to be told and retold as an example of the impact that one young girl can have.

In this case, Leela's initiative and perseverance are examples of "choti bachi ki chudai." Her efforts demonstrate that even small actions can add up to make a big difference, and her story serves as a reminder that everyone has the power to create positive change. choti bachi ki chudai

Another example might be a young girl named Leela who lives in a city and is passionate about environmental conservation. Despite her young age, Leela decides to take action and starts a campaign to reduce plastic waste in her neighborhood. She rallies her friends and family, and together they work to raise awareness and make a positive impact on their community. In this example, Aisha's actions demonstrate "choti bachi

In many Indian households, it is common to hear stories of young girls who exhibit extraordinary bravery, whether it is standing up to bullies, helping those in need, or overcoming personal challenges. These stories are often told with great pride and admiration, and the phrase "choti bachi ki chudai" is used to acknowledge and celebrate the girl's courage. Despite her young age, Leela decides to take

"Choti bachi ki chudai" is a Hindi phrase that translates to "a young girl's bravery" or "a young girl's courage." It is often used to describe a situation where a young girl shows remarkable courage, resilience, or determination in the face of adversity.

Overall, "choti bachi ki chudai" is a powerful phrase that celebrates the courage and resilience of young girls. It serves as a reminder that bravery and determination can take many forms, and that even the smallest actions can have a significant impact.

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