20
0.0 0.5 1.0 1.5 2.0 2.5 3.0 0.0000
0.0002 0.0004 0.0006 0.0008 0.0010 0.0012
NOISE_LEVEL
POSITION_ERROR
0.0 0.5 1.0 1.5 2.0 2.5 3.0 0.0000
0.0001 0.0002 0.0003 0.0004
NOISE_LEVEL
POSITION_ERROR
proposed triangulation homogeneous triangulation (Hartley and Zisserman, 2005) Fig. 8. Effect of triangulation on position error.
center of distortion estimation. IEEE Trans. Pattern Analysis and Machine Intelligence 29, 1309–1321.
Hartley, R., Zisserman, A., 2005. Multiple View Geometry in Computer Vision.
Cambridge University Press, Cambridge, UK.
Kazhdan, M., Bolitho, M., Hoppe, H., 2006. Poisson surface reconstruction, in: Eurographics Symposium on Geometry Processing, pp. 61–70.
K¨oser, K., 2009. Geometric Estimation with Local Affine Frames and Free-form Surfaces. Ph.D. thesis. University of Kiel.
K¨oser, K., Beder, C., Koch, R., 2008. Conjugate rotation: Parameterization and estimation from an affine feature correspondence, in: Conf. on Computer Vision and Pattern Recognition, pp. 1–8.
K¨oser, K., Koch, R., 2008. Differential spatial resection-pose estimation using a single local image feature, in: Proc. European Conf. on Computer Vision, Springer. pp. 312–325.
Kutulakos, K., Seitz, S., 1999. A theory of shape by space carving, in: Proc.
International Conf. on Computer Vision, pp. 307–314.
Lemaire, T., Berger, C., Jung, I.K., Lacroix, S., 2007. Vision-based SLAM:
Stereo and monocular approaches. International Journal of Computer Vision 74, 343–364.
Li, B., Heng, L., Koser, K., Pollefeys, M., 2013. A multiple-camera system calibration toolbox using a feature descriptor-based calibration pattern, in:
2013 IEEE/RSJ International Conference on Intelligent Robots and Sys-tems, IEEE. pp. 1301–1307.
Magda, S., Kriegman, D.J., Zickler, T., Belhumeur, P.N., 2001. Beyond lam-bert: Reconstructing surfaces with arbitrary brdfs, in: Proc. International Conf. on Computer Vision, IEEE. pp. 391–398.
Megyesi, Z., K´os, G., Chetverikov, D., 2006. Dense 3D reconstruction from images by normal aided matching. Machine Graphics & Vision 15, 3–28.
Micusik, B., Pajdla, T., 2004. Autocalibration and 3D reconstruction with non-central catadioptric cameras, in: Conf. on Computer Vision and Pattern Recognition, pp. I–58.
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaf-falitzky, F., Kadir, T., Van Gool, L., 2005. A comparison of affine region detectors. International Journal of Computer Vision 65, 43–72.
Moln´ar, J., Chetverikov, D., 2014. Quadratic transformation for planar mapping of implicit surfaces. Journal of Mathematical Imaging and Vision 48, 176–
184.
Moln´ar, J., Frohlich, R., Chetverikov, D., Kat´o, Z., 2014a. 3D Reconstruction of Planar Patches Seen by Omnidirectional Cameras, in: International Conf.
on Digital Image Computing: Techniques and Applications, pp. 1–8.
Moln´ar, J., Huang, R., Kat´o, Z., 2014b. 3D Reconstruction of Planar Surface Patches: A Direct Solution, in: ACCV Workshop on Big Data in 3D Com-puter Vision, pp. 286–300.
Molton, N., Davison, A., Reid, I., 2004. Locally planar patch features for real-time structure from motion, in: Proceedings of the British Machine Vision Conference, BMVA Press. pp. 90.1–90.10.
Morel, J.M., Yu, G., 2009. ASIFT: A new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences 2, 438–469.
Oxford University, KU Leuven, INRIA, CMP, 2007. Affine Covariant Features.
www.robots.ox.ac.uk/˜vgg/research/affine/.
Perd’och, M., Matas, J., Chum, O., 2006. Epipolar geometry from two corre-spondences, in: Proc. International Conf. on Pattern Recognition, pp. 215–
219.
Riggi, F., Toews, M., Arbel, T., 2006. Fundamental matrix estimation via TIP-transfer of invariant parameters, in: Proc. International Conf. on Pat-tern Recognition, pp. 21–24.
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J., 2007. Segmenting, mod-eling, and matching video clips containing multiple moving objects. IEEE Trans. Pattern Analysis and Machine Intelligence 29, 477–491.
Scaramuzza, D., Martinelli, A., Siegwart, R., 2006. A flexible technique for accurate omnidirectional camera calibration and structure from mo-tion, in: IEEE International Conference on Computer Vision Systems, 2006 ICVS’06., IEEE. pp. 45–45.
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R., 2006. A compari-son and evaluation of multi-view stereo reconstruction algorithms, in: Conf.
on Computer Vision and Pattern Recognition, pp. 519–528.
Sonka, M., Hlavac, V., Boyle, R., 2008. Image Processing, Analysis, and Ma-chine Vision. Thomson.
Svoboda, T., Pajdla, T., 2002. Epipolar geometry for central catadioptric cam-eras. International Journal of Computer Vision 49, 23–37.
Tanacs, A., Majdik, A., Molnar, J., Rai, A., Kato, Z., 2014. Establishing cor-respondences between planar image patches, in: International Conference on Digital lmage Computing: Techniques and Applications (DICTA), IEEE.
pp. 1–7.
Tuytelaars, T., Mikolajczyk, K., 2008. Local invariant feature detectors: a survey, in: Foundations and Trends in Computer Graphics and Vision. Now Publishers Inc.. volume 3, pp. 177–280.
University of Szeged, Institute for Computer Science and Control, 2008.
Patch-Based Multiview Reconstruction of Planar Surfaces. inf.u-szeged.hu/projectdirs/rgvc/collabreconba2015/.
Xu, Y., Monasse, P., G´eraud, T., Najman, L., 2014. Tree-based morse regions:
A topological approach to local feature detection. IEEE Transactions on Image Processing 23, 5612–5625.
Ying, X., Mei, X., Yang, S., Wang, G., Rong, J., Zha, H., 2014. Imposing differential constraints on radial distortion correction, in: Asian Conference on Computer Vision, Springer. pp. 384–398.
Zickler, T., Belhumeur, P., Kriegman, D., 2002. Helmholtz stereopsis: Exploit-ing reciprocity for surface reconstruction. International Journal of Computer Vision 49, 215–227.
ACCEPTED MANUSCRIPT
21
Fig. 9. Surface reconstruction for building facades.
J´ozsef Moln´arwas born in 1964. He graduated from the Budapest Univer-sity of Technology and Economics in 1988 (MSc in mechanical engineer-ing). After 20 years of software de-velopment he began his PhD studies in 2008, defended his thesis in 2011 at the E¨otv¨os Lor´and University, Bu-dapest. His research interests are in the fields of 3D reconstruction, dif-ferential geometry, variational image processing methods including seg-mentation, optical flow estimation and shape analysis.
Iv´an Eichh´ardtwas born in 1989.
He received his MSc degree in Com-puter Science in 2014 from the E¨otv¨os Lor´and University, Budapest, Hungary. He is a student of the PhD School of Computer Science at this university. He is also a mem-ber of the Systems and Control Lab at the Institute for Computer Science and Control (MTA SZTAKI). His main fields of research are computer vision, image processing, structure-from-motion, 3D reconstruction and sensor fusion.
ACCEPTED MANUSCRIPT
22
Fig. 10. Surface reconstruction of the Bear. Input images and two views of the reconstructed surface.
Fig. 11. Surface reconstruction of ‘Herz-Jesu-P8’.
ACCEPTED MANUSCRIPT
23
Fig. 12. Surface reconstruction (Barath and Eichhardt, 2016) of ‘fountain-P11’.