Discrete-Continuous Optimization for Large-scale Structure from Motion

Recent work in structure from motion (SfM) has successfully built 3D models from large unstructured collections of images downloaded from the Internet. Most approaches use incremental algorithms that solve progressively larger bundle adjustment problems. These incremental techniques scale poorly as the number of images grows, and can drift or fall into bad local minima. We present an alternative formulation for SfM based on finding a coarse initial solution using a hybrid discrete-continuous optimization, and then improving that solution using bundle adjustment. The initial optimization step uses a discrete Markov random field (MRF) formulation, coupled with a continuous LevenbergMarquardt refinement. The formulation naturally incorporates various sources of information about both the cameras and the points, including noisy geotags and vanishing point estimates. We test our method on several large-scale photo collections, including one with measured camera positions, and show that ...

• Type: Journal
• Year: 2011
• Where: CVPR
• Authors: David Crandall, Andrew Owens, Noah Snavely, Daniel Huttenlocher
• Keywords: Bundle Adjustment, Bundle Adjustment Problems, Computer Vision, CVPR 2011, Incremental Bundle Adjustment