Dense 3D reconstruction from images by normal aided matching

• Autorzy: Megyesi Z. , Kós G. , Chetverikov D.
• Języki publikacji: EN

Abstrakty

EN

3D models play an increased role in today's computer applications. As a result, there is a need for flexible and easy to use measuring devices that produce 3D models of real world objects. 3D scene reconstruction is a quickly evolving field of computer vision, which aims at creating 3D models from images of a scene. Although many problems of the reconstruction process have been solved, the use of photographs as an information source involves some practical difficulties. Therefore, accurate and dense 3D reconstruction remains a challenging task. We discuss dense matching of surfaces in the case when the images are taken from a wide baseline camera setup. Some recent studies use a region-growing based dense matching framework, and improve accuracy through estimating the apparent distortion by local affine transformations. In this paper we present a way of using pre-calculated calibration data to improve precision. We demonstrate that the new method produces a more accurate model.

Słowa kluczowe

EN

image based reconstruction; 3D scene reconstruction; stereo; wide-baseline; dense matching

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2006
• Tom: Vol. 15, No. 1
• Strony: 3--28
• Opis fizyczny: Bibliogr. 28 poz., il., wykr.

Twórcy

autor

Megyesi Z.

autor

Kós G.

autor

Chetverikov D.

• Computer and Automation Research Institute, Budapest, Kende u. 13-17, H-1111 Hungary,

Bibliografia

• [1] Shi J., Tomasi C.: Good features to track. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, June, 1994.
• [2] Zhang Z., Deriche R., Faugeras O., Luong Q.T.: A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Technical Report 2273, INRIA, 1994.
• [3] Hartley R., Sturm P.: Triangulation. 6th International Conference on Computer Analysis of Images and Patterns, Prague, Czech Republic, pp. 190-197, Sep., 1995.
• [4] Trajkovic M., Hedley M.: Robust recursive structure and motion recovery under affine projection. Proc. British Machine Vision Conference, Sept., 1997.
• [5] Lhuillier M.: Efficient dense matching for textured scenes using region growing. Proc. British Machine Vision Conf., pp. 700-709, 1998.
• [6] Sonka M., Hlavac V., Boyle R. D.: Image Processing, Analysis and Machine Vision, 1998, PWS, Boston, USA.
• [7] Trucco E., Verrio A.: Introductory Techniques for 3-D Computer Vision, 1998, Prentice Hall.
• [8] Hartley R. I., de Agapito L., Reid I. D., Hayman E.: Camera calibration and the search for infinity. ICCV, pages 510-517, 1999.
• [9] Tuytelaars T., Van Gool L.: Content-based image retrieval based on local affinely invariant regions. Proc 3rd Int. Conf. on Visual Information Systems, pp. 493-500, 1999.
• [10] Fusiello A., Roberto V., Trucco E.: Symmetric stereo with multiple windowing. International Journal of Pattern Recognition and Artificial Intelligence, 14:1053-1066, 2000.
• [11] Hartley R., Zisserman A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge, UK, 2000.
• [12] Tuytelaars T., Van Gool L.: Wide baseline stereo based on local, affinely invariant regions. Proc. British Machine Vision Conf., pp. 412-422, 2000.
• [13] Kós G.: An algorithm to triangulate surfaces in 3D using unorganised point clouds. Computing Suppl., 14:219-232, 2001.
• [14] Matas J., Chum O., Urban M., Pajdla T.: Robust Wide baseline Stereo from Maximally Stable Extremal Regions. Proc. British Machine Vision Conference, volume 1, pages 384-393, 2002.
• [15] Sara R.: Finding the largest unambiguous component of stereo matching. Proc. European Conf. on Computer Vision, vol. 2, pp. 900-914, 2002.
• [16] Scharstein D., Szeliski R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47:7-42, 2002.
• [17] Strecha C., Tuytelaars T., Van Gool L.: Dense matching of multiple wide baseline views. Proc. Int. Conf. on Computer Vision, vol. 2, pp. 1194-1201, 2003.
• [18] Jankó Z., Chetverikov D.: Photo-Consistency Based Registration of an Uncalibrated Image Pair to a 3D Surface Model Using Genetic Algorithm. Proc. 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, Thessaloniki, 2004.
• [19] Megyesi Z., Chetverikov D.: Affine propagation for surface reconstruction in wide baseline stereo. Proc. 17th International Conference on Pattern Recognition, 2004.
• [20] Megyesi Z. and Chetverikov D.: Enhanced surface reconstruction from wide baseline images. Proc. 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, 2004.
• [21] Nister D.: Untwisting a projective reconstruction. International Journal of Computer Vision, 60(2), pp. 165-183, 2004.
• [22] Pollefeys M., Van Gool L., Vergauwen M., Verbiest F., Cornells K., Tops J., Koch R.: Visual modeling with a hand-held camera. International Journal of Computer Vision, pp. 207-232, 2004.
• [23] Strecha C., Fransens R., Van Gool L.: Wide-baseline stereo from multiple views: a probabilistic account. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 552-559, 2004.
• [24] Loh A. M., Hartley R.: Shape from non-homogeneous, non-stationary, anisotropic, perspective texture. Proc. British Machine Vision Conf., pages 69-78, 2005.
• [25] Martinec D., Pajdla T.: 3D Reconstruction by Fitting Low-rank Matrices with Missing Data. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 198-205, 2005.
• [26] Zeng G., Paris S., Quan L., Lhuillier M.: Surface Reconstruction by Propagating 3D Stereo Data in Multiple 2D Images. Proc. European Conf. on Computer Vision, pp. 163-174, 2004.
• [27] Fraundorfer F., Schindlerl K., Bischof H.: Piecewise planar scene reconstruction from sparse correspondences. Image and Vision Computing, 24, 395-406, 2006.
• [28] Fitzgibbon A. W.: Monkey Dataset. http://www.robots.ox.ac.uk/ awf/ibr/, 2006.