CSfM: Community-based Structure from Motion
This work addresses the robustness-efficiency trade-off in 3D reconstruction for computer vision applications, presenting an incremental improvement by combining elements of existing methods.
The paper tackles the trade-off between robustness and efficiency in Structure-from-Motion by proposing an adaptive community-based method that partitions the epipolar geometry graph into communities for parallel reconstruction and merges results with a global similarity averaging technique. Experimental results show it outperforms many global SfM approaches in computational efficiency and achieves similar or better accuracy and robustness than many incremental SfM approaches.
Structure-from-Motion approaches could be broadly divided into two classes: incremental and global. While incremental manner is robust to outliers, it suffers from error accumulation and heavy computation load. The global manner has the advantage of simultaneously estimating all camera poses, but it is usually sensitive to epipolar geometry outliers. In this paper, we propose an adaptive community-based SfM (CSfM) method which takes both robustness and efficiency into consideration. First, the epipolar geometry graph is partitioned into separate communities. Then, the reconstruction problem is solved for each community in parallel. Finally, the reconstruction results are merged by a novel global similarity averaging method, which solves three convex $L1$ optimization problems. Experimental results show that our method performs better than many of the state-of-the-art global SfM approaches in terms of computational efficiency, while achieves similar or better reconstruction accuracy and robustness than many of the state-of-the-art incremental SfM approaches.