Abstract

Structure-from-Motion (SfM) methods can be broadly categorized as incremental or global according to their ways to estimate initial camera poses. While incremental system has advanced in robustness and accuracy, the ef- fificiency remains its key challenge. To solve this problem, global reconstruction system simultaneously estimates all camera poses from the epipolar geometry graph, but it is usually sensitive to outliers. In this work, we propose a new hybrid SfM method to tackle the issues of effificiency, accuracy and robustness in a unifified framework. More specififically, we propose an adaptive community-based rotation averaging method fifirst to estimate camera rotations in a global manner. Then, based on these estimated camera rotations, camera centers are computed in an incremental way. Extensive experiments show that our hybrid method performs similarly or better than many of the state-of-theart global SfM approaches, in terms of computational effifi- ciency, while achieves similar reconstruction accuracy and robustness with two other state-of-the-art incremental SfM approaches.