Topology-Based 3D Reconstruction of Mid-Level Primitives in Man-Made Environments

In this paper a novel reconstruction method is presented that uses the topological relationship of detected image features to create a highly abstract but semantically rich 3D model of the reconstructed scenes. In the first step, a combined image-based reconstruction of points and lines is performed based on the current state of art structure from motion methods. Subsequently, connected planar three-dimensional structures are reconstructed by a novel method that uses the topological relationships between the detected image features. The reconstructed 3D models enable a simple extraction of geometric shapes, such as rectangles, in the scene.

[1]  Jan-Michael Frahm,et al.  Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Helmut Mayer,et al.  High Quality Facade Segmentation Based on Structured Random Forest, Region Proposal Network and Rectangular Fitting , 2018 .

[3]  Helmut Mayer,et al.  A CONVOLUTIONAL NETWORK FOR SEMANTIC FACADE SEGMENTATION AND INTERPRETATION , 2016 .

[4]  Reinhard Koch,et al.  Structure and motion from line correspondences: Representation, projection, initialization and sparse bundle adjustment , 2014, J. Vis. Commun. Image Represent..

[5]  Jan-Michael Frahm,et al.  Building Rome on a Cloudless Day , 2010, ECCV.

[6]  Reinhard Koch,et al.  Pose Estimation from Line Correspondences: A Complete Analysis and a Series of Solutions , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Andrew Zisserman,et al.  New Techniques for Automated Architectural Reconstruction from Photographs , 2002, ECCV.

[8]  Helmut Mayer,et al.  BUILDING FACADE INTERPRETATION FROM IMAGE SEQUENCES , 2005 .

[9]  A Budroni,et al.  Automatic 3D modelling of indoor Manhattan-world scenes from laser data , 2010 .

[10]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

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

[12]  Horst Bischof,et al.  Improving Sparse 3D Models for Man-Made Environments Using Line-Based 3D Reconstruction , 2014, 2014 2nd International Conference on 3D Vision.

[13]  Alan L. Yuille,et al.  Manhattan World: compass direction from a single image by Bayesian inference , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Reinhard Koch,et al.  An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency , 2013, J. Vis. Commun. Image Represent..

[15]  Luc Van Gool,et al.  ATLAS: A Three-Layered Approach to Facade Parsing , 2016, International Journal of Computer Vision.

[16]  Reinhard Koch,et al.  Combined Precise Extraction and Topology of Points, Lines and Curves in Man-Made Environments , 2017, GCPR.

[17]  Markus Vincze,et al.  Room-structure estimation in Manhattan-like environments from dense 2½D range data using minumum entropy and histograms , 2011, 2011 IEEE Workshop on Applications of Computer Vision (WACV).

[18]  Dominik Wolters.  Automatic 3D Reconstruction of Indoor Manhattan World Scenes Using Kinect Depth Data , 2014, GCPR.

[19]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Richard Szeliski,et al.  Piecewise planar stereo for image-based rendering , 2009, 2009 IEEE 12th International Conference on Computer Vision.