Coupled structure-from-motion and 3D symmetry detection for urban facades

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.

[1]  Luc Van Gool,et al.  The cascaded Hough transform as an aid in aerial image interpretation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[2]  Jan-Michael Frahm,et al.  Detailed Real-Time Urban 3D Reconstruction from Video , 2007, International Journal of Computer Vision.

[3]  Jan-Michael Frahm,et al.  Repetition-based dense single-view reconstruction , 2011, CVPR 2011.

[4]  Daniel Cohen-Or,et al.  Non-local scan consolidation for 3D urban scenes , 2010, ACM Trans. Graph..

[5]  Manolis I. A. Lourakis,et al.  SBA: A software package for generic sparse bundle adjustment , 2009, TOMS.

[6]  Leonidas J. Guibas,et al.  Discovering structural regularity in 3D geometry , 2008, SIGGRAPH 2008.

[7]  Ping Tan,et al.  Symmetric architecture modeling with a single image , 2009, SIGGRAPH 2009.

[8]  CeylanDuygu,et al.  Coupled structure-from-motion and 3D symmetry detection for urban facades , 2014 .

[9]  Horst Bischof,et al.  What can missing correspondences tell us about 3D structure and motion? , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Loong Fah Cheong,et al.  Seeing double without confusion: Structure-from-motion in highly ambiguous scenes , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[12]  Dieter Schmalstieg,et al.  Robust Incremental Structure from Motion , 2010 .

[13]  Niloy J. Mitra,et al.  Symmetry in 3D Geometry: Extraction and Applications , 2013, Comput. Graph. Forum.

[14]  Long Quan Image-Based Modeling , 2009, accv 2009.

[15]  Venu Madhav Govindu Lie-algebraic averaging for globally consistent motion estimation , 2004, CVPR 2004.

[16]  Venu Madhav Govindu,et al.  Robustness in Motion Averaging , 2006, ACCV.

[17]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Marc Pollefeys,et al.  Disambiguating visual relations using loop constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Richard Szeliski,et al.  Structure from motion for scenes with large duplicate structures , 2011, CVPR 2011.

[20]  Tien-Tsin Wong,et al.  Resizing by symmetry-summarization , 2010, ACM Trans. Graph..

[21]  John Hart,et al.  ACM Transactions on Graphics , 2004, SIGGRAPH 2004.

[22]  Richard Szeliski,et al.  A Multi-stage Linear Approach to Structure from Motion , 2010, ECCV Workshops.

[23]  Marc Pollefeys,et al.  Handling Urban Location Recognition as a 2D Homothetic Problem , 2010, ECCV.

[24]  Niloy J. Mitra,et al.  Factored Facade Acquisition using Symmetric Line Arrangements , 2012, Comput. Graph. Forum.

[25]  Wolfram Burgard,et al.  Improving Data Association in Vision-based SLAM , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  Jianxiong Xiao,et al.  Image-based façade modeling , 2008, ACM Trans. Graph..

[27]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Marc Pollefeys,et al.  Interactive 3D architectural modeling from unordered photo collections , 2008, SIGGRAPH 2008.

[29]  Sikun Li,et al.  Sorting unorganized photo sets for urban reconstruction , 2012, Graph. Model..

[30]  Daniel Cohen-Or,et al.  2D-3D fusion for layer decomposition of urban facades , 2011, 2011 International Conference on Computer Vision.

[31]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[32]  Adrien Bartoli,et al.  Constrained Structure and Motion From Multiple Uncalibrated Views of a Piecewise Planar Scene , 2003, International Journal of Computer Vision.

[33]  Daniel G. Aliaga,et al.  A Survey of Urban Reconstruction , 2013, Comput. Graph. Forum.

[34]  Leonidas J. Guibas,et al.  Image webs: Computing and exploiting connectivity in image collections , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[35]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Eli Shechtman,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, ACM Trans. Graph..

[37]  Stephen P. Boyd,et al.  Graph Implementations for Nonsmooth Convex Programs , 2008, Recent Advances in Learning and Control.

[38]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[39]  Loong Fah Cheong,et al.  Multi-view repetitive structure detection , 2011, 2011 International Conference on Computer Vision.

[40]  Jan-Michael Frahm,et al.  Detecting Large Repetitive Structures with Salient Boundaries , 2010, ECCV.

[41]  Marc Pollefeys,et al.  Discovering and exploiting 3D symmetries in structure from motion , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[42]  Kun Zhou,et al.  Interactive images , 2012, ACM Trans. Graph..

[43]  Atsushi Iwata,et al.  Stereo Matching Algorithm Using a Weighted Average of Costs Aggregated by Various Window Sizes , 2006, ACCV.

[44]  Yong-Liang Yang,et al.  Interactive Facades Analysis and Synthesis of Semi‐Regular Facades , 2013, Comput. Graph. Forum.

[45]  Jana Kosecka,et al.  Detection and matching of rectilinear structures , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[46]  Roberto Cipolla,et al.  Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo , 2008, ECCV.

[47]  Tomás Pajdla,et al.  Robust Rotation and Translation Estimation in Multiview Reconstruction , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[48]  Noah Snavely,et al.  Scene Reconstruction and Visualization from Internet Photo Collections: A Survey , 2011, IPSJ Trans. Comput. Vis. Appl..

[49]  P. Heng,et al.  Resizing by symmetry-summarization , 2010, SIGGRAPH 2010.

[50]  Daniel Cohen-Or,et al.  SmartBoxes for interactive urban reconstruction , 2010, ACM Transactions on Graphics.

[51]  Leonidas J. Guibas,et al.  An Optimization Approach to Improving Collections of Shape Maps , 2011, Comput. Graph. Forum.