Limits of learning-based superresolution algorithms

International Journal of Computer Vision

Volumn 80, Issue 3, 2008, Pages 406-420

  Lin, Zhouchen ^a   He, Junfeng ^b   Tang, Xiaoou ^a   Tang, Chi Keung ^b  

^a MICROSOFT RESEARCH ASIA   (China)

^b HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

Author keywords

Learning based; Limits; Resolution; Superresolution

Indexed keywords

ALGORITHMS; CONTROL THEORY; COVARIANCE MATRIX; EDUCATION; ESTIMATION; IMAGE ACQUISITION; IMAGE ENHANCEMENT; LEARNING SYSTEMS; OPTICAL RESOLVING POWER; RISK PERCEPTION;

CLOSED FORM; EXPECTED RISK; GROUND TRUTH; HIGH-RESOLUTION IMAGES; LEARNING-BASED; LIMITS; LOW-RESOLUTION IMAGES; LOWER BOUNDS; MAGNIFICATION FACTORS; MEAN VECTORS; NATURAL IMAGES; REAL IMAGES; RESOLUTION; ROOT MEAN SQUARED ERRORS; SR ALGORITHMS; SR TECHNIQUE; SUPER RESOLVED IMAGING; SUPER-RESOLUTION ALGORITHMS; SUPERRESOLUTION;

LEARNING ALGORITHMS;

EID: 52449090194     PISSN: 09205691     EISSN: 15731405     Source Type: Journal    
DOI: 10.1007/s11263-008-0148-2     Document Type: Article

References (41)

1. S. Baker T. Kanade 2002 Limits on super-resolution and how to break them IEEE Transactions on Pattern Analysis and Machine Intelligence 24 9 1167 1183
2. Bégin, I., & Ferrie, F. R. (2004). Blind super-resolution using a learning-based approach. In Proc. int. conf. pattern recognition, August 2004 (Vol. 1, pp. 549-552).
3. Bishop, C. M., Blake, A., & Marthi, B. (2003). Super-resolution enhancement of video. In C.M. Bishop, & B. Frey (Eds.), Proc. artificial intelligence and statistics. Society for Artificial Intelligence and Statistics.
4. Borman, S., & Stevenson, R. L. (1998). Spatial resolution enhancement of low-resolution image sequences: a comprehensive review with directions for future research (Technical report). University of Notre Dame.
5. F. M. Candocia J. C. Principe 1999 Super-resolution of images based on local correlations IEEE Transaction on Neural Network 10 2 372 380
6. Capel, D., & Zisserman, A. (2001). Super-resolution from multiple views using learnt image models. In Proc. computer vision and pattern recognition (pp. II 627-634).
7. Chang, T.-L., Liu, T.-L., & Chuang, J.-H. (2006). Direct energy minimization for super-resolution on nonlinear manifolds. In Proc. European conf. computer vision (pp. IV 281-294).
8. Chang, H., Yeung, D., & Xiong, Y. (2004). Super-resolution through neighbor embedding. In Proc. computer vision and pattern recognition (Vol. 1, pp. 275-282).
9. Dedeoǧlu, G., Kanade, T., & August, J. (2004). High-zoom video hallucination by exploiting spatio-temporal regularities. In Proc. computer vision and pattern recognition (pp. II 151-158).
10. M. Elad A. Feuer 1997 Restoration of single super-resolution image from several blurred, noisy and down-sampled measured images IEEE Transactions on Image Processing 6 12 1646 1658
11. Fan, W., & Yeung, D.-Y. (2007). Image hallucination using neighbor embedding over visual primitive manifolds. In Proc. computer vision and pattern recognition.
12. S. Farsiu D. Robinson M. Elad P. Milanfar 2004 Advances and challenges in super-resolution International Journal of Imaging Systems and Technology 14 2 47 57
13. Freeman, W. T., & Pasztor, E. C. (1999). Learning low-level vision. In Proc. 7th int. conf. computer vision, Corfu, Greece (pp. 1182-1189).
14. B. K. Gunturk A. U. Batur Y. Altunbasak M. H. Hayes III R. M. Mersereau 2003 Eigenface-domain super-resolution for face recognition IEEE Transactions on Image Processing 12 5 597 606
15. R. C. Hardie K. J. Barnard E. E. Amstrong 1997 Joint map registration and high-resolution image estimation using a sequence of undersampled images IEEE Transactions on Image Processing 6 12 1621 1633
16. Hertzmann, A., Jacobs, C. E., Oliver, N., Curless, B., & Salesin, D. H. (2001). Image analogies. In SIGGRAPH.
17. S. P. Kim W. Y. Su 1993 Recursive high-resolution reconstruction of blurred multiframe images IEEE Transactions on Image Processing 2 534 539
18. T. Komatsu K. Aizawa T. Igarashi T. Saito 1993 A signal-processing based method for acquiring very high resolution image with multiple cameras and its theoretical analysis IEE Proceedings on Communications, Speech and Vision 140 1 19 25
19. O. Kursun O. Favorov 2003 Single-frame super-resolution by inference from learned features Istanbul University Journal of Electrical & Electronics Engineering 3 1 673 681
20. Li, Y., & Lin, X. (2004a). An improved two-step approach to hallucinating faces. In Proc. 3rd int. conf. image and graphics (pp. 298-301).
21. Li, Y., & Lin, X. (2004b). Face hallucination with pose variation. In Proc. 6th IEEE int. conf. automatic face and gesture recognition (pp. 723-728).
22. Z. Lin H.-Y. Shum 2004 Fundamental limits of reconstruction-based superresolution algorithms under local translation IEEE Transactions on Pattern Analysis and Machine Intelligence 26 1 83 97
23. Lin, Z., He, J., Tang, X., & Tang, C.-K. (2007). Limits of learning-based superresolution algorithms. In Int. conf. computer vision.
24. Liu, C., Shum, H.-Y., & Zhang, C. S. (2001). A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In Proc. computer vision and pattern recognition (pp. 192-198).
25. Liu, W., Lin, D., & Tang, X. (2005a). Hallucinating faces: TensorPatch super-resolution and coupled residue compensation. In Proc. computer vision and pattern recognition (pp. II 478-484).
26. Liu, W., Lin, D., & Tang, X. (2005b). Neighbor combination and transformation for hallucinating faces. In IEEE int. conf. multimedia and expo (ICME), Amsterdam, Netherlands.
27. Liu, W., Lin, D., & Tang, X. (2005c). Face hallucination through dual associative learning. In IEEE int. conf. image processing (ICIP), Genova, Italy.
28. Miravet, C., & Rodríguez, F.B. (2003). A hybrid MLP-PNN architecture for fast image superresolution. In Int. conf. artificial neural network (pp. 417-424).
29. N. Nguyen P. Milanfar 2000 An efficient wavelet-based algorithm for image superresolution IEEE International Conference Image Processing (ICIP) 2 351 354
30. S. C. Park M. K. Park M. G. Kang 2003 Super-resolution image reconstruction: a technical overview IEEE Signal Processing Magazine 20 3 21 36
31. A. J. Patti M. I. Sezan A. M. Tekalp 1997 Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time IEEE Transaction on Image Processing 6 8 1064 1076
32. Pickup, L. C., Roberts, S. J., & Zisserman, A. (2003). A sampled texture prior for image super-resolution. Advances in Neural Information Processing Systems (pp. 1587-1594).
33. S. H. Rhee M. G. Kang 1999 Discrete cosine transform based regularized high-resolution image reconstruction algorithm Optical Engineering 38 8 1348 1356
34. N. R. Shah A. Zakhor 1999 Resolution enhancement of color video sequences IEEE Transactions on Image Processing 8 879 885
35. Shiryaev, A. N. (1995). Probability. Berlin: Springer.
36. A. Srivastava A. B. Lee E. P. Simoncelli S.-C. Zhu 2003 On advances in statistical modeling of natural images Journal of Mathematical Imaging and Vision 18 17 33
37. Sun, J., Tao, H., & Shum, H.-Y. (2003). Image hallucination with primal sketch priors. In Proc. computer vision and pattern recognition (pp. II 729-736).
38. Tsai, R. Y., & Huang, T. S. (1984). Multipleframe image restoration and registration. In Advances in computer vision and image processing (pp. 317-339). Greenwich: JAI Press.
39. Vapnik, V. N. (1998). Statistical learning theory. New York: Wiley.
40. Wilson, R. (2000). MGMM: multiresolution Gaussian mixture models for computer vision. In Proc. int. conf. pattern recognition (pp. I 212-215).
41. Zhang, L., & Pan, F. (2002). A new method of images super-resolution restoration by neural networks. In Proc. 9th int. conf. neural information processing (Vol. 5, pp. 2414-2418), 18-22 November.