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

Reshmi Nair Photoshoot Extra Quality May 2026

One day, Reshmi received an exciting offer to collaborate with a prominent fashion brand for a high-end photoshoot. The brand wanted her to create stunning images that would showcase their latest collection, and they gave her complete creative freedom.

On the day of the photoshoot, Reshmi arrived early, eager to get started. She set up her gear, and her team began to prepare the models. As she started directing the models, Reshmi's creative vision began to unfold. reshmi nair photoshoot extra quality

Reshmi Nair, a talented and up-and-coming photographer, was known for her keen eye for detail and creative vision. She had built a reputation for delivering exceptional results, and her clients loved working with her. One day, Reshmi received an exciting offer to

Reshmi's dedication to delivering extra quality had paid off, and she continued to push the boundaries of her craft, inspiring others with her creativity and expertise. She set up her gear, and her team

The photoshoot was a huge success, and the images exceeded everyone's expectations. The brand was thrilled with the results, and Reshmi's clients were impressed by her extra quality and attention to detail.

Reshmi was thrilled and immediately began brainstorming ideas. She spent hours researching, planning, and preparing for the shoot. She carefully selected a beautiful outdoor location, assembled a team of skilled professionals, and prepared her equipment.

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