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

Fu10 Day Watching 18 New Access

Day 4 — Lake Motosu & Shiraito Falls 8. Lake Motosu west shore (Motosuko) — viewpoint used on currency note. 9. Shiraito Falls (near Fujinomiya) — waterfall with Fuji background (seasonal visibility). Note: Motosu best at sunrise for reflections.

Day 5 — Subashiri & Fujinomiya approaches 10. Subashiri 5th Station area (lower altitude viewpoint). 11. Fujinomiya Sengen Shrine precincts — temple foregrounds and rituals. Logistics: Combine cultural shots in Fujinomiya afternoon. fu10 day watching 18 new

Day 6 — Gotemba & southern plain 12. Gotemba Peace Park — wide plain view with Fuji rising. 13. Susono/Gotemba highway rest stop viewpoints — dramatic low-angle shots. Notes: Golden hour views from open plains. Day 4 — Lake Motosu & Shiraito Falls 8

Day 7 — Mount Tenjo & Shirane/Oshino 14. Mount Tenjo (ropeway near Lake Kawaguchi) — alternate panoramic angle. 15. Oshino Hakkai village ponds — classic clear ponds with Fuji reflections. Logistics: Combine with local crafts and food photos. Shiraito Falls (near Fujinomiya) — waterfall with Fuji

Day 9 — Higher-elevation hike or seasonal meadow Option A (non-climbing): 18A. Mount Fuji 6th–7th station approach viewpoint (accessible via guided tours) — alpine foregrounds. Option B (short hike): 18B. Fujinomiya Trail short summit approach viewpoint (safe, lower elevation) — dramatic volcanic slopes. Notes: For high-elevation viewpoints consider weather, permit/guides, and seasonal closures.

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