Image Mosaicing and Super-resolution
Inhaltsverzeichnis
Reference
Capel, David (2001). Image Mosaicing and Super-resolution. Ph. D. thesis, Oxford University, Dept. of Engineering Science. ISBN: 978-1-4471-1049-1 (Print) 978-0-85729-384-8 (Online)
DOI
http://link.springer.com/book/10.1007%2F978-0-85729-384-8
Abstract
The thesis investigates the problem of how information contained in multiple, overlap- ping images of the same scene may be combined to produce images of superior quality. This area, generically titled frame fusion, offers the possibility of reducing noise, extend- ing the field of view, removal of moving objects, removing blur, increasing spatial resolu- tion and improving dynamic range. As such, this research has many applications in fields as diverse as forensic image restoration, computer generated special effects, video image compression, and digital video editing. An essential enabling step prior to performing frame fusion is image registration, by which an accurate estimate of the point-to-point mapping between views is computed. A robust and efficient algorithm is described to automatically register multiple images using only information contained within the images themselves. The accuracy of this method, and the statistical assumptions upon which it relies, are investigated empirically. Two forms of frame-fusion are investigated. The first is image mosaicing, which is the alignment of multiple images into a single composition representing part of a 3D scene. Various methods of presenting the composite image are demonstrated, and in particular, a novel algorithm is developed for automatically choosing an optimal viewing transfor- mation for certain cases. In addition, a new and efficient method is demonstrated for the matching of point features across multiple views. The second frame-fusion method is super-resolution, which aims to restore poor qual- ity video sequences by removing the degradations inherent in the imaging process. The framework presented here uses a generative model of the imaging process, which is dis- cussed in detail and an efficient implementation presented. An algorithm is developed which seeks a maximum likelihood estimate under this model, and the factors affecting its performance are investigated analytically and empirically. The use of “generic” prior image models in a Bayesian framework is described and shown to produce dramatically improved super-resolution results. Finally, super-resolution algorithms are developed which make use of image models which are tuned to specific classes of image. These algorithms are shown to produce results of comparable or better quality than those using generic priors, while having a lower computational complexity. The technique is applied to images of text and faces. Throughout this work, the performance of the algorithms is evaluated using real image sequences. The applications demonstrated include the separation of latent marks from cluttered, non-periodic backgrounds in forensic images; the automatic creation of full 360 ◦ panoramic mosaics; and the super-resolution restoration of various scenes, including text and faces in low-quality video.
Extended Abstract
Bibtex
Used References
[1] http://www.apple.com/quicktime/products/qt/overview/qtvr.html.
[3] http://www.robots.ox.ac.uk/∼improofs.
[4] http://www.salientstills.com.
[5] http://www.smoothmove.com.
[6] E. Adelson. Layered representations for vision and video. In ICCV Workshop on the Representation of Visual Scenes, 1995.
[7] M. Aggarwal and N. Ahuja. High dynamic range panoramic imaging. In Proc. 8th In- ternational Conference on Computer Vision, Vancouver, Canada, pages I: 2–9, 2001.
[8] M. Aggarwal, H. Hua, and N. Ahuja. On cosine-fourth and vignetting effects in real lenses. In Proc. 8th International Conference on Computer Vision, Vancouver, Canada, pages I: 472–479, 2001.
[9] P. Anandan and M. Irani. Video representation and manipulation using mosaics. In R. Benosman and S.B. Kang, editors, Panoramic Vision: Sensors, Theory, Applica- tions, pages 393–424. Springer, New York, 2001.
[10] S. Baker and T. Kanade. Limits on super-resolution and how to break them. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2000.
[11] B. Bascle, A. Blake, and A. Zisserman. Motion deblurring and super-resolution from an image sequence. In Proc. 4th European Conference on Computer Vision, Cam- bridge, pages 312–320. Springer-Verlag, 1996.
[12] B. Bascle and R. Deriche. Region tracking through image sequences. In Proc. 5th International Conference on Computer Vision, Boston, 1995.
[13] P. Beardsley, P. Torr, and A. Zisserman. 3D model acquisition from extended image sequences. In Proc. European Conference on Computer Vision, LNCS 1064/1065, pages 683–695. Springer-Verlag, 1996.
[14] J. Besag. Spatial interaction and the statistical analysis of lattice systems. Journal of the Royal Statistical Society, pages 192–236, 1974.
[15] J. Besag. On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society, B-48(3):259–302, 1986.
[16] M.J. Black and P. Anandan. The robust estimation of multiple motions: Paramet- ric and piecewise-smooth flow-fields. Computer Vision and Image Understanding, 63(1):75–104, January 1996.
[17] A. Blake and A. Zisserman. Visual Reconstruction. MIT Press, Cambridge, USA, August 1987.
[18] M. Bober, N. Georgis, and J. Kittler. On accurate and robust estimation of funda- mental matrix. In Proc. 7th British Machine Vision Conference, Edinburgh, 1996.
[19] S. Borman, K. Sauer, and C. Bouman. Nonlinear prediction methods for estimation of clique weighting parameters in nongaussian image models. In SPIE Conferences, volume 3459, San Diego, CA, July 1998.
[20] S. Borman and R.L. Stevenson. Simultaneous multi-frame MAP super-resolution video enhancement using spatio-temporal priors. In Proc. IEEE International Con- ference on Image Processing, 1999.
[21] C. Bouman and K. Sauer. A generalized gaussian image model for edge-preserving map estimation. Image Processing, 2(3):296–310, July 1993.
[22] S.K. Bramble and P.M. Fabrizi. Observations on the effects of image processing func- tions on fingerma rk data in the fourier domain. In SPIE Conferences, volume 2567, pages 138–144, 1995.
[23] S.K. Bramble and J. Jackson. Operational experience of fingermark enhancement by frequency domain filtering. Journal of Forensic Sciences, 39:920–932, 1994.
[24] R.H. Byrd, R.B. Schnabel, and G.A. Shultz. Approximate solution of the trust region problem by minimization over two-dimensional subspaces. Mathematical Program- ming, 40:247–263, 1988.
[25] A. Can, C.V. Stewart, and B. Roysam. Robust hierarchical algorithm for construct- ing a mosaic from images of the curved human retina. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, pages II:286–292, 1999.
[26] F. M. Candocia and J. C. Principe. Super-resolution of images based on local correla- tions. IEEE Trans. Neural Networks, 10(2):372, 1999.
[27] J. F. Canny. A computational approach to edge detection. IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 8(6):679–698, 1986.
[28] D. Capel and A. Zisserman. Automated mosaicing with super-resolution zoom. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, pages 885–891, June 1998.
[29] D. P. Capel and A. Zisserman. Super-resolution enhancement of text image sequences. In Proc. International Conference on Pattern Recognition, pages 600–605, 2000.
[30] D. P. Capel, A. Zisserman, S. Bramble, and D. Compton. An automatic method for the removal of unwanted, non-periodic patterns from forensic images. In Proc. of SPIE, Boston, Massachussets, USA, volume 3576, 1-6 November 1998.
[31] R. Chan, T. Chan, and C. Wong. Cosine transform based precontioners for total vari- ation minimization problems in image processing. In Proc. 2nd IMACS Symposium on Iterative Methods, Blagoevgrad, Bulgaria, pages 311–329, June 1995.
[32] T. Chan, P. Blomgren, P. Mulet, and C. K. Wong. Total variation image restoration: Numerical methods and extensions. In Proc. IEEE International Conference on Image Processing, pages III:384–xx, 1997.
[33] T. F. Chan, G. H. Golub, and P. Mulet. A nonlinear primal-dual method for to- tal variation-based image restoration. SIAM Journal on Scientific Computing, 20(6):1964–1977, 1999.
[34] P. Cheeseman, B. Kanefsky, R. Kraft, and J. Stutz. Super-resolved surface reconstruc- tion from multiple images. Technical report, NASA, 1994.
[35] S. Chen. Quicktime VR - an image-based approach to virtual environment naviga- tion. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics, 1995.
[36] S. Chen and L. Williams. View interpolation for image synthesis. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics, 1993.
[37] S. Coorg, N. Master, and S. Teller. Acquisition of a large pose-mosaic dataset. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, pages 872–878, 1998.
[38] S. Coorg and S. Teller. Spherical mosaics with quaternions and dense correlation. International Journal of Computer Vision, 37(3):259–273, June 2000.
[39] A. Criminisi, I. Reid, and A. Zisserman. Radico - radial distortion correction from single view. Technical Report OUEL, Dept. Engineering Science, University of Ox- ford, Parks Road, Oxford OX1 3PJ, U. K., 1998.
[40] A. Criminisi, I. Reid, and A. Zisserman. Single view metrology. International Journal of Computer Vision, 40(2):123–148, November 2000.
[41] G. Cross. Surface Reconstruction from Image Sequences: Texture and Apparent Con- tour Constraints. PhD thesis, University of Oxford, 2000.
[42] G. Cross, A. W. Fitzgibbon, and A. Zisserman. Parallax geometry of smooth sur- faces in multiple views. In Proc. 7th International Conference on Computer Vision, Kerkyra, Greece, pages 323–329, September 1999.
[43] G. Cross and A. Zisserman. Quadric surface reconstruction from dual-space geome- try. In Proc. 6th International Conference on Computer Vision, Bombay, India, pages 25–31, January 1998.
[44] G. Cross and A. Zisserman. Surface reconstruction from multiple views using appar- ent contours and surface texture. In A. Leonardis, F. Solina, and R. Bajcsy, editors, NATO Advanced Research Workshop on Confluence of Computer Vision and Com- puter Graphics, Ljubljana, Slovenia, pages 25–47, 2000.
[45] Cross G. and Zisserman A. Quadric surface reconstruction from dual-space geometry. Accepted to International Conference on Computer Vision, Bombay, 1998.
[46] J.E. Davis. Mosaics of scenes with moving objects. In Proc. IEEE Conference on Com- puter Vision and Pattern Recognition, Santa Barbara, pages 354–360, 1998.
[47] L. de Agapito, E. Hayman, and I. Reid. Self-calibration of a rotating camera with varying intrinsic parameters. In Proc. 9th British Machine Vision Conference, Southampton, 1998.
[48] F. Dellaert, S. Thrun, and C. Thorpe. Mosaicing a large number of widely dispersed, noisy, and distorted images: A Bayesian approach. Technical report, School of Com- puter Science, Carnegie Mellon University, 1999.
[49] F. Dellaert, S. Thrun, and C. Thrope. Jacobian images of super-resolved texture maps for model based motion estimation and tracking. In Proc. IEEE Workshop on Appli- cations of Computer Vision, page Session 1A, 1998.
[50] J. E. Dennis Jr. and R.N. Schnabel. Numerical methods for unconstrained optimiza- tion and nonlinear equations, volume 16. Society for Industrial and Applied Mathe- matics (SIAM), Philadelphia, PA, 1996.
[51] F. Devernay and O. D. Faugeras. Automatic calibration and removal of distortion from scenes of structured environments. In SPIE Conferences, volume 2567, San Diego, CA, July 1995.
[52] Marquardt. D.W. An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2):431–441, 1963.
[53] A. Efros and T. Leung. Texture synthesis by non-parametric sampling. In Proc. 7th International Conference on Computer Vision, Kerkyra, Greece, pages 1039–1046, September 1999.
[54] M. Elad. Super-resolution reconstruction of images. PhD thesis, Technion, Israel, 1996.
[55] M. Elad and A. Feuer. Super-resolution reconstruction of continuous image sequence - the non-casual approach. Technical report, Technion, Israel, 1996.
[56] M. Elad and A. Feuer. Super-resolution reconstruction of continuous image se- quences. In Proc. IEEE International Conference on Image Processing, page 27AP5, 1999.
[57] M. Elad and A. Feuer. Super-resolution reconstruction of image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(9):817, September 1999.
247filtering approach. Image Processing, 8(3):387, March 1999.
[59] H. Engl, M. Hanke, and A. Neubauer. Regularization of Inverse Problems. Kluwer Academic Publishers, Dordrecht, 1996.
[60] P.E. Eren, M.I. Sezan, and A.M. Tekalp. Robust region-based high-resolution image reconstruction from low-resolution video. In Proc. IEEE International Conference on Image Processing, page 16P7, 1996.
[61] P.E. Eren, M.I. Sezan, and A.M. Tekalp. Robust, object based high resolution image reconstruction from low resolution video. IP, 6(10):1446–1451, October 1997.
[62] M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fit- ting with applications to image analysis and automated cartography. Comm. Assoc. Comp. Mach., 24(6):381–395, 1981.
[63] W. Freeman and E. Pasztor. Learning low-level vision. In Proc. International Con- ference on Computer Vision, pages 1182–1189, 1999.
[64] W. Freeman and E. Pasztor. Learning to estimate scenes from images. Technical report, Mitsubishi Electric Research Laboratory, 1999.
[65] W. Freeman and E. Pasztor. Markov networks for low-level vision. Technical report, Mitsubishi Electric Research Laboratory, 1999.
[66] W.T. Freeman, E.C. Pasztor, and O.T. Carmichael. Learning low-level vision. Inter- national Journal of Computer Vision, 40(1):25–47, October 2000.
[67] S. Geman and D Geman. Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 6(6):721–741, November 1984.
[68] A.R. German. Analog & Digital Image Processing of Latent Fingerprints eds. H.C. Lee and R.E. Gaensslen, chapter 7, pages 193–208. Elsevier, 1991.
[69] P. E. Gill and W. Murray. Algorithms for the solution of the nonlinear least-squares problem. SIAM J. Numerical Analysis, 15(5):977–992, 1978.
[70] P.E. Gill, W. Murray, and M.H. Wright. Practical Optimization. Academic Press, Lon- don, UK, 1981.
[71] G. H. Golub and C. F. Van Loan. Matrix Computations. The Johns Hopkins University Press, Baltimore, MD, second edition, 1989.
[72] R. Gonzalez and P. Wintz. Image Processing. Addison-Wesley, 1987.
[73] C. Groetsch. The Theory of Tikhonov Regularization for Fredholm Equations of the First Kind. Pitman, 1984.
[74] B. Gunturk, Y. Altunbasak, and R. Mersereau. Bayesian resolution-enhancement framework for transform-coded video. In Proc. IEEE International Conference on Image Processing, 2001.
[75] C. J. Harris and M. Stephens. A combined corner and edge detector. In Proc. 4th Alvey Vision Conference, Manchester, pages 147–151, 1988.
[76] R. I. Hartley. Self-calibration from multiple views with a rotating camera. In Proc. European Conference on Computer Vision, LNCS 800/801, pages 471–478. Springer- Verlag, 1994.
[77] R. I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cam- bridge University Press, ISBN: 0521623049, 2000.
[78] R.I. Hartley. Self-calibration of stationary cameras. International Journal of Com- puter Vision, 22(1):5–23, February 1997.
[79] P. J. Huber. Robust Statistics. John Willey and Sons, 1981.
[80] P. J. Huber. Projection pursuit. Annals of Statistics, 13:433–475, 1985. [81] M. Irani and P. Anandan. Video indexing based on mosaic representations. Proceed- ings of IEEE, 86(5):905–921, May 1998.
[82] M. Irani and P. Anandan. About direct methods. In W. Triggs, A. Zisserman, and R. Szeliski, editors, Vision Algorithms: Theory and Practice, LNCS. Springer Verlag, 2000.
[83] M. Irani, P. Anandan, J. Bergen, R. Kumar, and S. Hsu. Efficient representations of video sequences and their applications. Signal Processing: Image Communication, 8(4):327–351, May 1996.
[84] M. Irani, P. Anandan, and S. Hsu. Mosaic based representations of video sequences and their applications. In Proc. 5th International Conference on Computer Vision, Boston, pages 605–611, 1995.
[85] M. Irani, S. Hsu, and P. Anandan. Video compression using mosaic representations. Signal Processing: Image Communication, 7(4):529–552, November 1995.
[86] M. Irani and S. Peleg. Improving resolution by image registration. Graphical Models and Image Processing, 53:231–239, 1991.
[87] M. Irani and S. Peleg. Motion analysis for image enhancement:resolution, occlu- sion, and transparency. Journal of Visual Communication and Image Representa- tion, 4:324–335, 1993.
[88] M. Irani, B. Rousso, and S. Peleg. Detecting and tracking multiple moving objects using temporal integration. In G. Sandini, editor, Proc. 2nd European Conference on Computer Vision, Santa Margharita Ligure, Italy, pages 282–287. Springer-Verlag, 1992.
[89] M. Irani, B. Rousso, and S. Peleg. Computing occluding and transparent motions. International Journal of Computer Vision, 12(1):5–16, 1994.
[90] A.K. Jain. Fundamentals of Digital Image Processing. Prentice-Hall, 1989.
249[91] S.B. Kang and R. Szeliski. 3-d scene data recovery using omnidirectional multibase- line stereo. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 364–370, 1996.
[92] S.B. Kang and R. Szeliski. 3-d scene data recovery using omnidirectional multi- baseline stereo. International Journal of Computer Vision, 25(2):167–183, November 1997.
[93] M. Kendall and A. Stuart. The Advanced Theory of Statistics. Charles Griffin and Company, London, 1983.
[94] D. Keren, S. Peleg, and R. Brada. Image sequence enhancement using sub-pixel dis- placements. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 742–746, 1988.
[95] R. Kumar, P. Anandan, M. Irani, J. Bergen, and K. Hanna. Representation of scenes from collections of images. In ICCV Workshop on the Representation of Visual Scenes, 1995.
[96] H. J. Larson. Introduction to Probability Theory and Statistical Inference. John Wiley, 1982.
[97] K. Levenberg. A method for the solution of certain non-linear problems in least squares. Quarterly Applied Mathematics, II(2):164–168, 1944.
[98] S. Z. Li. Markov Random Field Modeling in Computer Vision. Springer-Verlag, Tokyo, 1995.
[99] S. Mann and R. W. Picard. Virtual bellows: Constructing high quality stills from video. In Proc. IEEE International Conference on Image Processing, 1994.
[100] S. Mann and R. W. Picard. Video orbits of the projective group: A new perspective on image mosaicing. Technical report, MIT, 1996.
[101] L. McMillan and G. Bishop. Plenoptic modeling: An image-based rendering system. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics, 1995.
[102] J. More and G. Toraldo. On the solution of large quadratic programming problems with bound constraints. SIAM J. Optimization, 1(1):93–113, 1991.
[103] J.J Mor ́e and D.C. Sorensen. Computing a trust region step. SIAM Journal on Scien- tific and Statistical Computing, 4(3):553–572, 1983.
[104] N. Nguyen, Milanfar P., and G.H. Golub. A computationally efficient image superres- olution algorithm. Image Processing, March 2001.
[105] B.A. Olshausen and D.J. Field. Natural image statistics and efficient coding. Network, pages 7:333–339, 1996.
[106] A.J. Patti and Y. Altunbasak. Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants. Image Processing, 10(1):179–186, January 2001.
250[107] A.J. Patti, M.I. Sezan, and A.M. Tekalp. Robust methods for high-quality stills from interlaced video in the presence of dominant motion. IEEE Trans. Circuits and Sys- tems for Video Technology, 7(2):328–342, April 1997.
[108] A.J. Patti, M.I. Sezan, and A.M. Tekalp. Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time. Image Processing, 6(8):1064– 1076, August 1997.
[109] S. Peleg. Panoramic mosaics by manifold projection. Technical report, Hebrew Uni- versity of Jerusalem, 1997.
[110] S. Peleg, M. Ben-Ezra, and Y. Pritch. Omnistereo: Panoramic stereo imaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(3):279–290, March 2001.
[111] S. Peleg, M. Ben-Ezra, and Y. Pritch. Panoramic imaging with horizontal stereo. In R. Benosman and S.B. Kang, editors, Panoramic Vision: Sensors, Theory, Applica- tions, pages 143–160, 2001.
[112] S. Peleg and J. Herman. Panoramic mosaics by manifold projection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 1997.
[113] S. Peleg and J. Herman. Panoramic mosaics with videobrush. In Image Understand- ing Workshop (DARPA), pages 261–264, 1997.
[114] S. Peleg, D. Keren, and L. Schweitzer. Improving image resolution using subpixel motion. Pattern Recognition Letters, 5:223–226, 1987.
[115] S. Peleg, B. Rousso, A. Rav-Acha, and A. Zomet. Mosaicing with strips on adaptive manifolds. In Panoramic Vision: Sensors, Theory, Applications, pages 309–325, 2001.
[116] W.K. Pratt. Digital Image Processing. John Wiley & Sons, 1991.
[117] W. Press, B. Flannery, S. Teukolsky, and W. Vetterling. Numerical Recipes in C. Cam- bridge University Press, 1988.
[118] S. E. Reichenbach, S. K. Park, and R. Narayanswamy. Characterizing digitial image aquisition devices. Optical Engineering, 30(2):170–177, 1991.
[119] J. A. Rice. Mathematical Statistics and Data Analysis. Wadsworth and Brooks, Cali- fornia, 1988.
[120] M.A. Robertson, S. Borman, and R.L. Stevenson. Estimation theoretic approach to dynamic range improvement through multiple exposures. In Proc. IEEE International Conference on Image Processing, page 27AO3, 1999.
[121] B. Rousso, S. Peleg, and I. Finci. Mosaicking with generalized strips. In Image Un- derstanding Workshop (DARPA), pages 255–260, 1997.
[122] B. Rousso, S. Peleg, I. Finci, and A. Rav-Acha. Universal mosaicing using pipe pro- jection. In Proc. 6th International Conference on Computer Vision, Bombay, India, pages 945–952, 1998.
[123] L. Rudin, F. Guichard, and P. Yu. Video super-resolution via contrast-invariant mo- tion segmentation and frame fusion (with applications to forensic video evidence). In Proc. IEEE International Conference on Image Processing, page 27PS1, 1999.
[124] P. D. Sampson. Fitting conic sections to ‘very scattered’ data: An iterative refinement of the bookstein algorithm. Computer Vision, Graphics, and Image Processing, 18:97– 108, 1982.
[125] S.S. Saquib, C.A. Bouman, and K. Sauer. ML parameter estimation for markov ran- dom fields with applications to bayesian tomography. Image Processing, 7(7):1029– 1044, July 1998.
[126] S.S. Saquib, J. Zheng, C.A Bouman, and K. Sauer. Provably convergent coordinate descent in statistical tomographic reconstruction. In Proc. IEEE International Confer- ence on Image Processing, volume 2, 1996.
[127] Harpreet S. Sawhney and Rakesh Kumar. True multi-image alignment and its ap- plication to mosaicing and lens distortion correction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(3):235–243, 1999.
[128] H.S. Sawhney, S. Hsu, and R. Kumar. Robust video mosaicing through topology in- ference and local to global alignment. In Proc. European Conference on Computer Vision, 1998.
[129] H.S. Sawhney, R. Kumar, G. Gendel, J. Bergen, D. Dixon, and V. Paragano. Video- brush: Experiences with consumer video mosaicing. In Proc. IEEE Workshop on Ap- plications of Computer Vision, page Session 2A, 1998.
[130] Y.Y. Schechner and S.K. Nayar. Generalized mosaicing. In Proc. 8th International Conference on Computer Vision, Vancouver, Canada, pages I: 17–24, 2001.
[131] C. Schmid, R. Mohr, and C. Bauckhage. Comparing and evaluating interest points. In Proc. International Conference on Computer Vision, pages 230–235, 1998.
[132] R. R. Schultz and R. L. Stevenson. Extraction of high-resolution frames from video sequences. IEEE Transactions on Image Processing, 5(6):996–1011, June 1996.
[133] K. Schutte and A. Vossepoel. Accurate mosaicing of scanned maps,or how to generate a virtual A0 scanner. In Annual Conference for the Advance School of Computing, pages 353–359, 1995.
[134] C. Segall, R. Molina, A. Katsaggelos, and J. Mateos. Bayesian high-resolution recon- struction of low-resolution compressed video. In Proc. IEEE International Conference on Image Processing, 2001.
[135] S. Seitz and C. Dyer. Physically-valid view synthesis by image interpolation. In ICCV Workshop on the Representation of Visual Scenes, 1995.
[136] A. Shashua and S. Toelg. The quadric reference surface: Theory and applications. International Journal of Computer Vision, 23(2):185–198, 1997.
252[137] H. Shekarforoush and R. Chellappa. Adaptive super-resolution for predator video sequences. In Image Understanding Workshop (DARPA), pages 995–1002, 1998.
[138] H Shekarforoush and R. Chellappa. Data-driven multichannel super-resolution with application to video sequences. Journal of the Optical Society of America, 16(3):481–492, March 1999.
[139] S. D. Silvey. Statistical Inference. Penguin, Harmondsworth, Middlesex, 1970.
[140] E.P. Simoncelli. Statistical models for images: Compression, restoration and synthe- sis. In Asilomar97, 1997.
[141] C. Slama. Manual of Photogrammetry. American Society of Photogrammetry, Falls Church, VA, USA, 4th edition, 1980.
[142] V.N. Smelyanskiy, P. Cheeseman, D. Maluf, and R. Morris. Bayesian super-resolved surface reconstruction from images. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, pages I:375–382, 2000.
[143] M. R. Spiegel. Theory and Problems of Statistics 2/ed. Mc Graw Hill, 1992.
[144] G. P. Stein. Lens distortion calibration using point correspondences. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, 1997.
[145] D. Strong, Blomgren. D., and T. Chan. Spatially adaptive local feature-driven total variation minimizing image restoration. In SPIE Conferences, volume 3167, 1997.
[146] R. Szeliski. Image mosaicing for tele-reality applications. Technical report, Digital Equipment Corporation, Cambridge, USA, 1994.
[147] R. Szeliski and S. Heung-Yeung. Creating full view panoramic image mosaics and environment maps. In Proceedings of the ACM SIGGRAPH Conference on Computer Graphics, 1997.
[148] R. Szeliski and S. B. Kang. Direct methods for visual scene reconstruction. In ICCV Workshop on the Representation of Visual Scenes, 1995.
[149] S. Teller. Automated urban model acquisition: Project rationale and status. In Image Understanding Workshop (DARPA), pages 455–462, 1998.
[150] A.N. Tikhonov and V.Y. Arsenin. Solutions of Ill-Posed Problems. V.H. Winston & Sons, John Wiley & Sons, Washington D.C., 1977.
[151] N. Tiller and T. Tiller. Conviction through enhanced fingerprint identification. FBI Law Enforcement Bulletin, 61(12):16–17, December 1992.
[152] B. Tom and A. Katsaggelos. Reconstruction of a high-resolution image by simultane- ous registration, restoration and interpolation of low-resolution images. In Proc. IEEE International Conference on Image Processing, 1995.
[153] B.C. Tom and A.K. Katsaggelos. Resolution enhancement of video sequences using motion compensation. In Proc. IEEE International Conference on Image Processing, 1996.
[154] P. H. S. Torr. Motion segmentation and outlier detection. PhD thesis, Dept. of Engi- neering Science, University of Oxford, 1995.
[155] P. H. S. Torr and D. W. Murray. Outlier detection and motion segmentation. Technical Report 1987/93, University of Oxford, 1993.
[156] P. H. S. Torr and D. W. Murray. A review of robust methods to estimate the fundamen- tal matrix. Accepted to IJCV, 1996.
[157] P. H. S. Torr and A. Zisserman. Computing multiple view relations. OUEL Report, 1997.
[158] P. H. S. Torr and A. Zisserman. Robust parameterization and computation of the trifocal tensor. Image and Vision Computing, 15:591–605, 1997.
[159] P. H. S. Torr and A. Zisserman. Robust computation and parameterization of multi- ple view relations. In Proc. 6th International Conference on Computer Vision, Bom- bay, India, pages 727–732, January 1998.
[160] P. H. S. Torr and A. Zisserman. MLESAC: A new robust estimator with application to estimating image geometry. Computer Vision and Image Understanding, 78:138– 156, 2000.
[161] P. H. S. Torr, A. Zisserman, and S. Maybank. Robust detection of degenerate config- urations for the fundamental matrix. Computer Vision and Image Understanding, 71(3):312–333, September 1998.
[162] W. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon. Bundle adjustment: A mod- ern synthesis. In W. Triggs, A. Zisserman, and R. Szeliski, editors, Vision Algorithms: Theory and Practice, LNCS. Springer Verlag, 2000.
[163] C.J. Tsai, P. Karunaratne, N.P. Galatsanos, and A.K. Katsaggelos. Compressed video enhancement with information from the encoder. In Proc. IEEE International Con- ference on Image Processing, 1999.
[164] R. Tsai and T. Huang. Multiframe image restoration and registration. Advances in Computer Vision and Image Processing, 1:317–339, 1984.
[165] Y. R. Tsai. An efficient and accurate camera calibration technique for 3D machine vision. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 1986.
[166] Y. Tsin, V. Ramesh, and T. Kanade. Statistical calibration of the ccd imaging pro- cess. In Proc. 8th International Conference on Computer Vision, Vancouver, Canada, pages I: 480–487, 2001.
[167] M. Turk and A.P. Pentland. Face recognition using eigenfaces. In Proc. IEEE Confer- ence on Computer Vision and Pattern Recognition, pages 586–591, 1991.
[168] H. Ur and D. Gross. Improved resolution from subpixel shifted pictures. Graphical Models and Image Processing, 54(2):181–186, March 1992.
[169] C. Vogel. Total variation regularization for ill-posed problems. Technical report, De- partment of Mathematical Sciences, Montana State University., 1993.
254[170] C. R. Vogel and M. E. Oman. Fast, robust total variation based reconstruction of noisy, blurred images. Image Processing, 7(6):813–824, June 1998.
[171] W.J. Watling. Using the FFT in forensic digital image enhancement. Journal of Foren- sic Identification, 43(6):573–584, 1993.
[172] J.S. Yedidia, W.T. Freeman, and Y. Weiss. Generalized belief propagation. Technical Report TR-2000-26, Mitsubishi Electric Research Laboratory, 2000.
[173] L. Zelnik-Manor and M. Irani. Multi-frame alignment of planes. In Proc. IEEE Con- ference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, pages I:151–156, 1999.
[174] L. Zelnik-Manor and M. Irani. Multi-frame estimation of planar motion. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 22(10):1105–1116, October 2000.
[175] J. Zheng, S.S. Saquib, K. Sauer, and C.A. Bouman. Parallelizable bayesian tomogra- phy algorithms with rapid, guaranteed convergence. Image Processing, 9(10):1745– 1759, October 2000.
[176] A. Zomet and S. Peleg. Efficient super-resolution and applications to mosaics. In Proc. International Conference on Pattern Recognition, pages Vol I: 579–583, 2000.
Links
Full Text
http://www.robots.ox.ac.uk/~vgg/publications/papers/capel01a.pdf
