Machine Vision and Applications

, Volume 23, Issue 5, pp 903–920 | Cite as

Efficient large-scale multi-view stereo for ultra high-resolution image sets

Original Paper

Abstract

We present a new approach for large-scale multi-view stereo matching, which is designed to operate on ultra high-resolution image sets and efficiently compute dense 3D point clouds. We show that, using a robust descriptor for matching purposes and high-resolution images, we can skip the computationally expensive steps that other algorithms require. As a result, our method has low memory requirements and low computational complexity while producing 3D point clouds containing virtually no outliers. This makes it exceedingly suitable for large-scale reconstruction. The core of our algorithm is the dense matching of image pairs using DAISY descriptors, implemented so as to eliminate redundancies and optimize memory access. We use a variety of challenging data sets to validate and compare our results against other algorithms.

Keywords

Multi-view stereo 3D reconstruction DAISY High-resolution images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alvarez L., Deriche R., Weickert J., Sanchez J.: Dense disparity map estimation respecting image discontinuities: a PDE and scale-space based approach. J. Mach. Learning Res. 13(1/2), 3–21 (2002)Google Scholar
  2. 2.
    Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: European Conference on Computer Vision (2006)Google Scholar
  3. 3.
    Frahm, J.-M., Georgel, P., Gallup, D., Johnson, T., Raguram, R., Jen, Y.-H., Wu, C., Dunn, E., Clipp, B., Lazebnik, S., Pollefeys, M.: Building Rome on a Cloudless Day. In: European Conference on Computer Vision (2010)Google Scholar
  4. 4.
    Fua P.: A parallel stereo algorithm that produces dense depth maps and preserves image features. Mach. Vis. Appl. Winter 6(1), 35–49 (1993)CrossRefGoogle Scholar
  5. 5.
    Fua P.: From multiple stereo views to multiple 3D surfaces. Comput. Vis. Image Underst. 24(1), 19–35 (1997)Google Scholar
  6. 6.
    Furukawa, Y., Ponce, J.: Accurate, dense, and robust multi-view stereopsis. IEEE Trans. Pattern Anal. Mach. Intel. 99 (preprint, 2009)Google Scholar
  7. 7.
    Goesele, M., Snavely, N., Curless, B., Hoppe, H., Seitz, S.M.: Multi-view stereo for community photo collections, pp. 1–8. In: International Conference on Computer Vision (2007)Google Scholar
  8. 8.
    Hiep, V.H., Keriven, R., Labatut, P., Pons, J.-P.: Towards high-resolution large-scale multi-view stereo, pp. 1430–1437. In: Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  9. 9.
    Hirschmüller H.: Stereo processing by semi-global matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30, 328–341 (2008)CrossRefGoogle Scholar
  10. 10.
    Hornung, A., Hornung, E., Kobbelt L.: Hierarchical volumetric multi-view stereo reconstruction of manifold surfaces based on dual graph embedding, pp. 503–510. In: Conference on Computer Vision and Pattern Recognition (2006)Google Scholar
  11. 11.
    Jancosek, M., Shekhovtsov, A., Pajdla, T.: Scalable multi-view stereo. In: 3DIM (2009)Google Scholar
  12. 12.
    Kazhdan, M., Bolitho, M., Hoppe H.: Poisson surface reconstruction, pp. 61–70. In: SGP ’06: Proceedings of the fourth Eurographics Symposium on Geometry processing (2006)Google Scholar
  13. 13.
    Lowe D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 20(2), 91–110 (2004)CrossRefGoogle Scholar
  14. 14.
    Pollefeys, M., Nistéer, D., Frahm, J.-M., Akbarzadeh, A., Mordohai, P., Clipp, B., Engels, C., Gallup, D., Kim, S.-J., Merrell, P., Salmi, C., Sinha, S., Talton, B., Wang, L., Yang, Q., Stewéenius, H., Yang, R., Welch, G., Towles, H.: Detailed real-time urban 3D reconstruction from video. Int. J. Comput. Vis. 78(2–3), 143–167 (2008). doi:10.007/s11263-007-0086-4
  15. 15.
    Salman, N., Yvinec, M.: Surface reconstruction from multi-view stereo. In: Asian Conference on Computer Vision (2009)Google Scholar
  16. 16.
    Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms, pp. 519–528. In: Conference on Computer Vision and Pattern Recognition (2006)Google Scholar
  17. 17.
    Starck, J., Miller, G., Hilton, A.: Volumetric stereo with silhouette and feature constraints. In: British Machine Vision Conference (September 2006)Google Scholar
  18. 18.
    Strecha, C.: Multi-view evaluation (2008). http://cvlab.epfl.ch/data
  19. 19.
    Strecha, C., Fransens, R., Van Gool L.: Wide-baseline stereo from multiple views: a probabilistic account. In: Conference on Computer Vision and Pattern Recognition (2004)Google Scholar
  20. 20.
    Strecha, C., Fransens, R., Van Gool, L.: Combined depth and outlier estimation in multi-view stereo. In: Conference on Computer Vision and Pattern Recognition (2006)Google Scholar
  21. 21.
    Strecha, C., Pylvanainen, T., Fua, P.: Dynamic and scalable large scale image reconstruction. In: Conference on Computer Vision and Pattern Recognition (June 2010)Google Scholar
  22. 22.
    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: Conference on Computer Vision and Pattern Recognition (2008)Google Scholar
  23. 23.
    Sun, J., Li, Y., Kang, S.B., Shum, H.-Y.: Symmetric stereo matching for occlusion handling, pp. 399–406. In: Conference on Computer Vision and Pattern Recognition (2005)Google Scholar
  24. 24.
    Tola, E.: Efficient large scale multiview stereo for ultra high resolution images (2011). http://www.engintola.com/research/emvs
  25. 25.
    Tola E., Lepetit V., Fua P.: Daisy: an efficient dense descriptor applied to wide baseline stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(5), 815–830 (2010)CrossRefGoogle Scholar
  26. 26.
    Tran, S., Davis, L.: 3D surface reconstruction using graph cuts with surface constraints, pp. 219–231. In: European Conference on Computer Vision (2006)Google Scholar
  27. 27.
    Tylecek, R., Sara, R.: Depth map fusion with camera position refinement. In: CVWW (2009)Google Scholar
  28. 28.
    Vogiatzis G., Hernandez Esteban C., Torr P.H.S., Cipolla R.: Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency. IEEE Trans. Pattern Anal. Mach. Intell. 29, 2241–2246 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2011

Authors and Affiliations

  1. 1.Aurvis LtdAnkaraTurkey
  2. 2.Computer Vision Laboratory, EPFLLausanneSwitzerland

Personalised recommendations