G-MASt3R-SfM: Graph-based View Pruning and Multi-stage Optimization for Robust SfM

2026-06-22

AI Summary

This work addresses the susceptibility of existing MASt3R-based structure-from-motion (SfM) methods to erroneous matches introduced by non-overlapping image pairs, which degrades pose estimation accuracy. To mitigate this issue, the authors propose a novel SfM pipeline that constructs a scene graph based on match confidence, followed by graph-structure pruning to eliminate outlier views. The framework further integrates geometric consistency verification and a progressive multi-stage incremental bundle adjustment (BA) optimization strategy to refine camera parameters from local to global scales. This approach significantly enhances robustness under noisy matching conditions, achieving state-of-the-art camera pose and 3D reconstruction accuracy on the ETH3D benchmark while effectively suppressing noise induced by incorrect correspondences.

Abstract

Structure from Motion (SfM) is essential for multi-view 3D reconstruction, however, its accuracy heavily relies on the accuracy of image matching. While the recent correspondence matching method, MASt3R, enables robust matching even under challenging conditions, it tends to generate incorrect correspondences for non-overlapping image pairs. Consequently, existing SfM methods using MASt3R, such as MASt3R-SfM, suffer from significant degradation in pose estimation accuracy as they incorporate these unreliable matches directly into optimization. To address this issue, we propose G-MASt3R-SfM, a novel SfM pipeline that enhances robustness through two key modules. First, the Graph-based View Pruning (GVP) module constructs a scene graph from matching confidence and geometrically prunes outlier views. Second, the Multi-Stage Optimization (MSO) module progressively refines camera parameters by expanding the optimization scope from local consistency to the global consistency. Experiments on the ETH3D dataset demonstrate that our method achieves state-of-the-art accuracy in both camera pose estimation and 3D reconstruction, effectively suppressing noise caused by outliers.

Problem

• Structure from Motion
• image matching
• outlier correspondences
• pose estimation
• non-overlapping views

Innovation

• Graph-based View Pruning
• Multi-stage Optimization
• Structure from Motion
• Robust Matching
• Outlier Suppression