VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors

2026-09-16

AI Summary

本文提出VGGT-GS SLAM系统，通过前馈先验和子图可微束调整优化未校准视频中的相机姿态和3D高斯地图，提高定位精度和渲染质量。

Abstract

We present VGGT-GS SLAM, a monocular 3D Gaussian Splatting SLAM system designed for uncalibrated videos. Starting from feed-forward VGGT pose and depth priors, our system performs submap differentiable bundle adjustment that jointly refines camera poses and a 3D Gaussian map, while optimizing submap-shared intrinsics and radial--tangential distortion through analytic calibration Jacobians. To improve global consistency, we introduce Gaussian-native alignment (GNA) for camera-anchored scale refinement between sequential submaps and verification of loop-closure candidates. Extensive experiments on standard indoor benchmarks show consistent improvements in localization accuracy and strong rendering quality under uncalibrated settings, establishing a strong baseline for uncalibrated Gaussian SLAM.

Problem

• Uncalibrated Monocular SLAM
• Gaussian Splatting
• Localization Accuracy

Innovation

• VGGT-GS SLAM
• Uncalibrated Monocular
• Gaussian Splatting
• Submap Differentiable Bundle Adjustment
• Gaussian-native Alignment (GNA)