Robust Line Segments Matching via Graph Convolution Networks

Line matching plays an essential role in structure from motion (SFM) and simultaneous localization and mapping (SLAM), especially in low-textured and repetitive scenes. In this paper, we present a new method of using a graph convolution network to match line segments in a pair of images, and we design a graph-based strategy of matching line segments with relaxing to an optimal transport problem. In contrast to hand-crafted line matching algorithms, our approach learns local line segment descriptor and the matching simultaneously through end-to-end training. The results show our method outperforms the state-of-the-art techniques, and especially, the recall is improved from 45.28% to 70.47% under a similar presicion. The code of our work is available at this https URL.

[1]  Francesc Moreno-Noguer,et al.  PL-SLAM: Real-time monocular visual SLAM with points and lines , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Yi Ma,et al.  End-to-End Wireframe Parsing , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Li Li,et al.  Hierarchical line matching based on Line-Junction-Line structure descriptor and local homography estimation , 2016, Neurocomputing.

[5]  Matthias Nießner,et al.  ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Cordelia Schmid,et al.  The Geometry and Matching of Lines and Curves Over Multiple Views , 2000, International Journal of Computer Vision.

[7]  Zhanyi Hu,et al.  Robust line matching through line-point invariants , 2012, Pattern Recognit..

[8]  Junchi Yan,et al.  Learning Combinatorial Embedding Networks for Deep Graph Matching , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[9]  Pascal Monasse,et al.  Robust SfM with Little Image Overlap , 2017, ArXiv.

[10]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[11]  Kai Li,et al.  Line segment matching and reconstruction via exploiting coplanar cues , 2017 .

[12]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[13]  Victor Lempitsky,et al.  Learnable Line Segment Descriptor for Visual SLAM , 2019, IEEE Access.

[14]  Horst Bischof,et al.  Efficient 3D scene abstraction using line segments , 2017, Comput. Vis. Image Underst..

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Luc Van Gool,et al.  Scale-invariant line descriptors for wide baseline matching , 2014, IEEE Winter Conference on Applications of Computer Vision.

[17]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[18]  Zhanyi Hu,et al.  MSLD: A robust descriptor for line matching , 2009, Pattern Recognit..

[19]  Manuel Lange,et al.  DLD: A Deep Learning Based Line Descriptor for Line Feature Matching , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Richard I. Hartley,et al.  A linear method for reconstruction from lines and points , 1995, Proceedings of IEEE International Conference on Computer Vision.

[21]  Manolis I. A. Lourakis,et al.  Matching disparate views of planar surfaces using projective invariants , 2000, Image Vis. Comput..

[22]  Lu Wang,et al.  Wide-baseline image matching using Line Signatures , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  van den Berg,et al.  UvA-DARE (Digital Academic Modeling Relational Data with Graph Convolutional Networks Modeling Relational Data with Graph Convolutional Networks , 2017 .

[25]  Jin Tang,et al.  GLMNet: Graph Learning-Matching Networks for Feature Matching , 2019, ArXiv.

[26]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[27]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[28]  Richard Sinkhorn.  A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices , 1964 .

[29]  Alper Yilmaz,et al.  Line Matching in Wide-Baseline Stereo: A Top-Down Approach , 2014, IEEE Transactions on Image Processing.

[30]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[31]  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..