cvpr cvpr2013 cvpr2013-47 cvpr2013-47-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Julio Zaragoza, Tat-Jun Chin, Michael S. Brown, David Suter
Abstract: We investigate projective estimation under model inadequacies, i.e., when the underpinning assumptions oftheprojective model are not fully satisfied by the data. We focus on the task of image stitching which is customarily solved by estimating a projective warp — a model that is justified when the scene is planar or when the views differ purely by rotation. Such conditions are easily violated in practice, and this yields stitching results with ghosting artefacts that necessitate the usage of deghosting algorithms. To this end we propose as-projective-as-possible warps, i.e., warps that aim to be globally projective, yet allow local non-projective deviations to account for violations to the assumed imaging conditions. Based on a novel estimation technique called Moving Direct Linear Transformation (Moving DLT), our method seamlessly bridges image regions that are inconsistent with the projective model. The result is highly accurate image stitching, with significantly reduced ghosting effects, thus lowering the dependency on post hoc deghosting.
[1] A. Agarwala, M. Dontcheva, M. Agrawala, S. Drucker, A. Colburn, B. Curless, D. Salesin, and M. Cohen. Interactive digital photomontage. In ACM SIGGRAPH, 2004. 2
[2] M. Alexa, J. Behr, D. Cohen-Or, S. Fleishman, D. Levin, and C. T. Silva. Computing and rendering point set surfaces. IEEE TVCG, 9(1):3–15, 2003. 1, 4
[3] A. Eden, M. Uyttendaele, and R. Szeliski. Seamless image stitching of scenes with large motions and expoure differences. In CVPR, 2006. 2
[4] J. Gao, S. J. Kim, and M. S. Brown. Constructing image panoramas using dual-homography warping. In CVPR, 2011. 3, 4, 5, 6
[5] G. H. Golub and C. F. van Loan. Matrix computations. The Johns Hopkins University Press, 3rd edition, 1996. 4
[6] G. Guennebaud and M. Gross. Algebraic point set surfaces. ACM TOG, 26(3), 2007. 2
[7] R. I. Hartley. In defense of the eight-point algorithm. IEEE TPAMI, 19(6):580–593, 1997. 3
[8] T. Igarashi, T. Moscovich, and J. F. Hughes. As-rigid-aspossible shape manipulation. ACM TOG, 24(3), 2005. 2
[9] W.-Y. Lin, S. Liu, Y. Matsushita, T.-T. Ng, and L.-F. Cheong. Smoothly varying affine stitching. In CVPR, 2011. 2, 4, 5, 6
[10] F. Liu, M. Gleicher, H. Jin, and A. Agarwala. Contentpreserving warps for 3d video stabilization. In ACM SIGGRAPH, 2009. 2, 4, 5
[11] A. Mynorenko, X. Song, and M. Carreira-Perpinan. Nonrigid point set registration: coherent point drift. In NIPS, 2007. 2
[12] S. Peleg, B. Rousso, A. Rav-Acha, and A. Zomet. Mosaicing on adaptive manifolds. IEEE TPAMI, 22(10), 2000. 1
[13] P. Perez, M. Gangnet, and A. Blake. Poisson image editing. In ACM SIGGRAPH, 2003. 2
[14] S. Schaefer, T. McPhail, and J. Warren. Image deformation using moving least squares. In SIGGRAPH, 2006. 1, 2, 4
[15] H.-Y. Shum and R. Szeliski. Construction of panoramic mosaics with global & local alignment. IJCV, 36(2), 2000. 2
[16] P. Stange. On the efficient update of the singular value decomposition. In App. Mathematics and Mechanics, 2008. 4
[17] R. Szeliski. Image alignment and stitching. In Handbook of Mathematical Models in Computer Vision, pages 273–292. Springer, 2005. 1, 2, 4, 5
[18] A. Vedaldi and B. Fulkerson. VLFeat: An open and portable library of computer vision algorithms. In ICM, MM ’ 10, pages 1469–1472, New York, NY, USA, 2010. ACM. 5 222333444422 Figure4.Qualit vecomparison (bestviewdonscren)o therailt cksimagepair.Redcirleshigl hteros.Litofacronyms and initialisms: SVA-Smoothly Varying Affine, DHW-Dual Homography Warps, CPW-Content Preserving Warps, APAP-As Projective As Possible Warps. 222333444533 Figure5.Qualit vecomparison (bestviewdonscren)o the mpleimagepair.Redcirleshigl hteros.Litofacronymsand initialisms: SVA-Smoothly Varying Affine, DHW-Dual Homography Warps, CPW-Content Preserving Warps, APAP-As Projective As Possible Warps. 222333444644