Learning-based natural geometric matching with homography prior

Learning-based natural geometric matching with homography prior

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while the importance of naturalness issue is argued simultaneously. To this end, a novel homography geometric matching architecture with homography prior is proposed. Specifically, two choices for different purposes in geometric matching are provided. When compositing homography prior with affine transformation, the alignment accuracy improves and all lines are preserved, which results in a more natural transformed image. When compositing homography prior with thin-plate-spline transformation, the alignment accuracy further improves. Experimental results on Proposal Flow dataset show that the proposed method outperforms state-of-the-art methods, both in terms of alignment accuracy and naturalness.


    1. 1)
      • 1. Ham, B., Cho, M., Schmid, C., et al: ‘Proposal flow’. Proc. of IEEE CVPR, Las Vegas, NV, USA, June 2016, pp. 34753484.
    2. 2)
    3. 3)
      • 3. Rocco, I., Arandjelovic, R., Sivic, J.: ‘Convolutional neural network architecture for geometric matching’. Proc. IEEE CVPR, Honolulu, HI, USA, July 2017, pp. 3948.
    4. 4)
      • 4. He, K.M., Zhang, X.Y., Ren, S.Q., et al: ‘Deep residual learning for image recognition’. Proc. of IEEE CVPR, Las Vegas, NV, USA, June 2016, pp. 770778.
    5. 5)
      • 5. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’. Proc. ICLR, San Diego, CA, USA, May 2015, pp. 12.
    6. 6)
    7. 7)
      • 7. Hartley, R., Zisserman, A.: ‘Multiple view geometry in computer vision’ (Cambridge University Press, Cambridge, UK, 2003).
    8. 8)
      • 8. Olivier Duchenne, O., Joulin, A., Ponce, J.: ‘A graph-matching kernel for object categorization’. Proc. of IEEE ICCV, Barcelona, Spain, November 2011, pp. 17921799.
    9. 9)
      • 9. Kim, J., Liu, C., Sha, F., et al: ‘Deformable spatial pyramid matching for fast dense correspondences’. Proc. of IEEE CVPR, Portland, OR, USA, June 2013, pp. 23072314.
    10. 10)
    11. 11)
    12. 12)
      • 12. Paszke, A., Gross, S., Chintala, S., et al: ‘Pytorch’,, 2017.
    13. 13)
      • 13. Rocco, I., Arandjelovic, I., Sivic, J.: ‘Webpage: Convolutional neural network architecture for geometric matching’,

Related content

This is a required field
Please enter a valid email address