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

Hydraulic Institute Engineering Data Book -

In the world of fluid handling, precision is not just a metric—it is a safety requirement, an economic driver, and an environmental necessity. For over a century, engineers have sought a singular, authoritative source to bridge the gap between theoretical fluid mechanics and real-world pump application. That source is the Hydraulic Institute Engineering Data Book .

In fluid dynamics, there is no substitute for the Hydraulic Institute. And at the core of the Hydraulic Institute lies its . About the Hydraulic Institute: Founded in 1917, HI is a global authority on pumps and pumping systems. Its standards and publications are used in over 100 countries. The Engineering Data Book is one of its flagship publications, updated continuously to reflect current technology and research. hydraulic institute engineering data book

Whether you are modeling a simple drainage system for a municipal airport or a complex hydrocarbon transfer network for a refinery, consider this book the final arbiter of truth. It sits on the desk of every competent pump engineer because it works: it is precise, it is peer-reviewed, and it is practical. In the world of fluid handling, precision is

| Feature | HI Engineering Data Book | Cameron Hydraulic Data (CRC) | Crane TP-410 | | :--- | :--- | :--- | :--- | | | Pump systems & NPSH | General pipe flow | Valves & fittings | | Fluid Coverage | Industrial (water & viscous) | Water & steam | Water, gas, steam | | Pump Specifics | Excellent (Affinity laws, Suction specific speed) | Good (Basic centrifugal) | Poor (Focus on control valves) | | Viscous Corrections | Industry Gold Standard (HI 9.6.7) | Generic | Tables only | | Best For | Pump specifiers & operators | Civil water works | Process plant design | In fluid dynamics, there is no substitute for

If you do not yet own a copy, visit the Hydraulic Institute’s official website (pumps.org). Purchase the current edition. Then, turn directly to Section E on viscous fluids or Section B on minor losses. Compare its values to whatever legacy spreadsheet you are currently using. The correction you find might save your next project from a catastrophic off-BEP operation.

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