Abstract
In this work, we consider the problem of propagation-based matching for 3D reconstruction, which deals with expanding a limited set of correspondences towards a quasi-dense map across two views. In general, propagation based methods capture well the scene structure. However, the recovered geometry often presents an overall choppy nature which can be attributed to matching errors and abrupt variations in the estimated local affine transformations. We propose to control the reconstructed geometry by means of a local patch fitting which corrects both the matching locations and affine transformations throughout the propagation process. In this way, matchings that propagate from geometrically consolidated locations bring coherence to both positions and affine transformations. Results of our approach are not only more visually appealing but also more accurate and complete as substantiated by results on standard benchmarks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lhuillier, M., Quan, L.: Quasi-dense reconstruction from image sequence. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part II. LNCS, vol. 2351, pp. 125–139. Springer, Heidelberg (2002)
Kannala, J., Brandt, S.: Quasi-dense wide baseline matching using match propagation. In: CVPR, pp. 1–8 (2007)
Chen, Q., Medioni, G.: A volumetric stereo matching method: application to image-based modeling. In: CVPR, Fort Collins, United States, vol. 1, pp. 1029–1034 (1999)
Cech, J., Sara, R.: Efficient sampling of disparity space for fast and accurate matching. In: CVPR, pp. 1–8 (2007)
Lhuillier, M., Quan, L.: A quasi-dense approach to surface reconstruction from uncalibrated images. PAMI 27, 418–433 (2005)
Yao, J., Cham, W.K.: 3D modeling and rendering from multiple wide-baseline images by match propagation. Sig. Process. Image Commun. 21, 506–518 (2006)
Furukawa, Y., Ponce, J.: Accurate, dense, and robust multi-view stereopsis. In: CVPR, pp. 1–8 (2007)
Koskenkorva, P., Kannala, J., Brandt, S.: Quasi-dense wide baseline matching for three views. In: ICPR, ICPR 2010, Washington, DC, USA, pp. 806–809. IEEE Computer Society (2010)
Otto, G., Chau, T.: A ‘region-growing’ algorithm for matching of terrain images. Image Vis. Comput. 7, 83–94 (1989)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Pajdla, T., Matas, J.G. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 40–54. Springer, Heidelberg (2004)
Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the Fourth Eurographics Symposium on Geometry Processing, SGP 2006, Aire-la-Ville, Switzerland, Switzerland, pp. 61–70. Eurographics Association (2006)
Ylimaki, M., Kannala, J., Holappa, J., Heikkila, J., Brandt, S.: Robust and accurate multi-view reconstruction by prioritized matching. In: ICPR, pp. 2673–2676. IEEE (2012)
Habbecke, M., Kobbelt, L.: A surface-growing approach to multi-view stereo reconstruction. In: CVPR, pp. 1–8 (2007)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. IJCV 65, 43–72 (2005)
Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)
Barnhill, R., Farin, G., Jordan, M., Piper, B.: Surface/surface intersection. Comput. Aided Des. 4, 3–16 (1987)
Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. PAMI 33, 500–513 (2011)
Tola, E., Lepetit, V., Fua, P.: Daisy: an efficient dense descriptor applied to wide-baseline stereo. PAMI 32, 815–830 (2010)
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, pp. 1–8 (2008)
Furukawa, Y., Ponce, J.: 3D photography dataset. http://www.cse.wustl.edu/furukawa/research/mview/index.html. Accessed 05 May 2014
Acknowledgments
The authors would like thank, the anonymous reviewers for their feedback on the paper, Juho Kannala for making his code publicly available, Christoph Strecha and Yasutaka Furukawa for their Multi-View datasets and Samuel Hornus for the face dataset. This work was funded by the ANR (Agence Nationale de la Recherche) under grant (PhysiGrafix ANR-09-CEXC-014-01).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Galindo, P.A., Zayer, R. (2015). Complementary Geometric and Optical Information for Match-Propagation-Based 3D Reconstruction. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision – ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9003. Springer, Cham. https://doi.org/10.1007/978-3-319-16865-4_45
Download citation
DOI: https://doi.org/10.1007/978-3-319-16865-4_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16864-7
Online ISBN: 978-3-319-16865-4
eBook Packages: Computer ScienceComputer Science (R0)