Parallel Structure from Motion from Local Increment to Global Averaging

In this paper, we tackle the accurate and consistent Structure from Motion (SfM) problem, in particular camera registration, far exceeding the memory of a single computer in parallel. Different from the previous methods which drastically simplify the parameters of SfM and sacrifice the accuracy, consistency, and robustness of the final reconstruction, we preserve as many connectivities among cameras as possible by proposing a camera clustering algorithm to divide a large SfM problem into smaller sub-problems in terms of camera clusters with overlapping. We then exploit a hybrid formulation that applies the relative motions from local incremental SfM into a global motion averaging framework and produce superior accurate and consistent global camera poses. Our scalable formulation in terms of camera clusters is highly applicable to the whole SfM pipeline including track generation, local SfM, 3D point triangulation and bundle adjustment, and is able to reconstruct the camera poses of a city-scale data-set containing more than one million high-resolution images with the state-of-the-art accuracy and robustness evaluated on benchmark, Internet, and sequential data-sets.