Repeated structures are ubiquitous in urban facades. Such repetitions lead to ambiguity in establishing correspondences across sets of unordered images. A decoupled structure-from-motion reconstruction followed by symmetry detection often produces errors: outputs are either noisy and incomplete, or even worse, appear to be valid but actually have a wrong number of repeated elements.We present an optimization framework for extracting repeated elements in images of urban facades, while simultaneously calibrating the input images and recovering the 3D scene geometry using a graph-based global analysis. We evaluate the robustness of the proposed scheme on a range of challenging examples containing widespread repetitions and nondistinctive features. These image sets are common but cannot be handled well with state-of-the-art methods. We show that the recovered symmetry information along with the 3D geometry enables a range of novel image editing operations that maintain consistency across the images. © 2014 ACM 0730-0301/2014/01-ART3 15.00.
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research received funding from the European Research Council under the European Unions 7th Framework Programme (FP/2007-2013)/ERC Grant Agreement 257453, ERC Starting Grant COSYM and European Community's Research Infrastructure Action grant agreement VISIONAIR 262044 under the 7th Framework Programme (FP7/2007-2013). This research was also supported by a Marie Curie CIG, an Adobe Research grant, and a UCL impact award.
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design