Structure from motion for scenes with large duplicate structures
- 1 June 2011
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3137-3144
- https://doi.org/10.1109/cvpr.2011.5995549
Abstract
Most existing structure from motion (SFM) approaches for unordered images cannot handle multiple instances of the same structure in the scene. When image pairs containing different instances are matched based on visual similarity, the pairwise geometric relations as well as the correspondences inferred from such pairs are erroneous, which can lead to catastrophic failures in the reconstruction. In this paper, we investigate the geometric ambiguities caused by the presence of repeated or duplicate structures and show that to disambiguate between multiple hypotheses requires more than pure geometric reasoning. We couple an expectation maximization (EM)-based algorithm that estimates camera poses and identifies the false match-pairs with an efficient sampling method to discover plausible data association hypotheses. The sampling method is informed by geometric and image-based cues. Our algorithm usually recovers the correct data association, even in the presence of large numbers of false pairwise matches.Keywords
This publication has 16 references indexed in Scilit:
- Exploiting Loops in the Graph of Trifocal Tensors for Calibrating a Network of CamerasLecture Notes in Computer Science, 2010
- Robust Rotation and Translation Estimation in Multiview ReconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Fast iterative alignment of pose graphs with poor initial estimatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Photo tourismACM Transactions on Graphics, 2006
- Lie-algebraic averaging for globally consistent motion estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- An efficient solution to the five-point relative pose problemIeee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Bundle Adjustment — A Modern SynthesisLecture Notes in Computer Science, 2000
- Generating random spanning trees more quickly than the cover timePublished by Association for Computing Machinery (ACM) ,1996
- Closed-form solution of absolute orientation using orthonormal matricesJournal of the Optical Society of America A, 1988
- Random sample consensusCommunications of the ACM, 1981