Match Selection and Refinement for Highly Accurate Two-View Structure from Motion

  • Zhe Liu
  • Pascal Monasse
  • Renaud Marlet
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8690)


We present an approach to enhance the accuracy of structure from motion (SfM) in the two-view case. We first answer the question: “fewer data with higher accuracy, or more data with less accuracy?” For this, we establish a relation between SfM errors and a function of the number of matches and their epipolar errors. Using an accuracy estimator of individual matches, we then propose a method to select a subset of matches that has a good quality vs. quantity compromise. We also propose a variant of least squares matching to refine match locations based on a focused grid and a multi-scale exploration. Experiments show that both selection and refinement contribute independently to a better accuracy. Their combination reduces errors by a factor of 1.1 to 2.0 for rotation, and 1.6 to 3.8 for translation.


Interest Point Fundamental Matrix Epipolar Line Structure From Motion Reprojection Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Supplementary material

978-3-319-10605-2_53_MOESM1_ESM.pdf (2.8 mb)
Electronic Supplementary Material (PDF 2,871 KB)


  1. 1.
    Aanæs, H., Dahl, A.L., Pedersen, K.S.: Interesting interest points. International Journal of Computer Vision 97(1), 18–35 (2012)CrossRefGoogle Scholar
  2. 2.
    Baatz, G., Köser, K., Chen, D., Grzeszczuk, R., Pollefeys, M.: Leveraging 3D city models for rotation invariant place-of-interest recognition. IJCV 96(3), 315–334 (2012), CrossRefGoogle Scholar
  3. 3.
    Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV 92(1), 1–31 (2011)CrossRefGoogle Scholar
  4. 4.
    Brooks, M.J., Chojnacki, W., Gawley, D., Van Den Hengel, A.: What value covariance information in estimating vision parameters? In: Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 302–308. IEEE (2001)Google Scholar
  5. 5.
    Cao, Y., McDonald, J.: Viewpoint invariant features from single images using 3D geometry. In: WACV (2009)Google Scholar
  6. 6.
    Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family. In: BMVC, pp. 1–12 (2009)Google Scholar
  7. 7.
    Chum, O., Matas, J.: Matching with PROSAC – progressive sample consensus. In: CVPR (2005)Google Scholar
  8. 8.
    Chum, O., Matas, J., Obdrzalek, S.: Enhancing RANSAC by generalized model optimization. In: ACCV (2004)Google Scholar
  9. 9.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. CACM 24(6) (1981)Google Scholar
  10. 10.
    Gruen, A.: Adaptive least squares correlation: a powerful image matching technique. S. Afr. J. of Photogrammetry, Remote Sensing and Cartography 14(3) (1985)Google Scholar
  11. 11.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2004)Google Scholar
  12. 12.
    Kanazawa, Y., Kanatani, K.: Do we really have to consider covariance matrices for image features? In: Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV), vol. 2, pp. 301–306. IEEE (2001)Google Scholar
  13. 13.
    Köser, K., Koch, R.: Perspectively invariant normal features. In: ICCV (2007)Google Scholar
  14. 14.
    Köser, K., Koch, R.: Exploiting uncertainty propagation in gradient-based image registration. In: BMVC (2008)Google Scholar
  15. 15.
    Liu, Z., Marlet, R.: Virtual line descriptor and semi-local graph matching method for reliable feature correspondence. In: BMVC (2012)Google Scholar
  16. 16.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  17. 17.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing 22(10), 761–767 (2004)CrossRefGoogle Scholar
  18. 18.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV 60(1), 63–86 (2004)CrossRefGoogle Scholar
  19. 19.
    Moisan, L., Stival, B.: A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix. IJCV 57(3), 201–218 (2004)CrossRefGoogle Scholar
  20. 20.
    Morel, J.M., Yu, G.: ASIFT: A new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences 2(2), 438–469 (2009)CrossRefzbMATHMathSciNetGoogle Scholar
  21. 21.
    Moulon, P., Monasse, P., Marlet, R.: Adaptive Structure from Motion with a contrario model estimation. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part IV. LNCS, vol. 7727, pp. 257–270. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  22. 22.
    Potůčková, M.: Image matching and its applications in photogrammetry. Ph.D. thesis, Aalborg Universitet (2004)Google Scholar
  23. 23.
    Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: CVPR (2008)Google Scholar
  24. 24.
    Sur, F., Noury, N., Berger, M.O.: Computing the uncertainty of the 8 point algorithm for fundamental matrix estimation. In: Proceedings of 19th British Machine Vision Conference (BMVC), pp. 96.1–96.10 (2008)Google Scholar
  25. 25.
    Tang, Z.: High precision in Camera calibration. Ph.D. thesis, ENS Cachan (2012)Google Scholar
  26. 26.
    Torr, P.H.S., Zisserman, A.: MLESAC: a new robust estimator with application to estimating image geometry. CVIU 78(1), 138–156 (2000)Google Scholar
  27. 27.
    Torr, P.H., Murray, D.W.: The development and comparison of robust methods for estimating the fundamental matrix. IJCV 24(3), 271–300 (1997)CrossRefGoogle Scholar
  28. 28.
    Wu, C., Clipp, B., Li, X., Frahm, J.M., Pollefeys, M.: 3D model matching with viewpoint-invariant patches (VIP). In: CVPR (2008)Google Scholar
  29. 29.
    Zeisl, B., Georgel, P.F., Schweiger, F., Steinbach, E.G., Navab, N., Munich, G.: Estimation of location uncertainty for scale invariant features points. In: Proceedings of 20th British Machine Vision Conference (BMVC), pp. 1–12 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Zhe Liu
    • 1
  • Pascal Monasse
    • 1
  • Renaud Marlet
    • 1
  1. 1.Université Paris-Est, LIGM (UMR 8049), ENPCMarne-la-ValléeFrance

Personalised recommendations