Single image super-resolution via self-similarity and low-rank matrix recovery
Tóm tắt
We propose a novel single-image super resolution (SISR) approach using self-similarity of image and the low-rank matrix recovery (LRMR). The method performs multiple upsampling steps with relatively small magnification factors to recover a desired high resolution image. Each upsampling process includes the following steps: First, a set of low/high resolution (LR/HR) patch pairs is generated from the pyramid of the input low resolution image. Next, for each patch of the unknown HR images, similar HR patches are found from the set of LR/HR patch pairs by the corresponding LR patch and are stacked into a matrix with approximately low rank. Then, the LRMR technique is exploited to estimate the unknown HR image patch. Finally, the back-projection technique is used to perform the global reconstruction. We tested the proposed method on fifteen images including humans, animals, plants, text, and medical images. Experimental results demonstrate the effectiveness of the proposed method compared with several representative methods for SISR in terms of quantitative metrics and visual effect.
Tài liệu tham khảo
Arya S, Mount DM (1993) Approximate nearest neighbor queries in fixed dimensions. In: Proceedings of the fourth annual ACM-SIAM symposium on discrete algorithms - SODA '93. Austin, Texas, USA, 25–27 January 1993, pp 271–280
Bagon S (2009) Matlab class for ANN. http://www.wisdom.weizmann.ac.il/~bagon/matlab.html
Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel ML (2012) Low complexity single image super-resolution based on nonnegative neighbor embedding. In: Proceedings British Machine Vision Conference 135:1–10
Chang H, Yeung D-Y, Xiong Y (2004) Super-resolution through neighbor embedding. IEEE Comput Soc Conf Comput Vis Pattern Recognit 1:275–282
Chen X, Qi C (2014) Low-rank neighbor embedding for single image super resolution. IEEE Signal Processing Letters. 21(1):79–82
Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process 16(8):2080–2095
Ding C, Zhou D, He X, Zha H (2006) R1-PCA: rotational invariant l1 -norm principal component analysis for robust subspace. In: Proceedings of the 23rd international conference on Machine learning - ICML '06. Pittsburgh, Pennsylvania, USA, 25–29 June 2006, pp 281–288
Dong W, Shi G, Li X (2013) Nonlocal image restoration with bilateral variance estimation: a low-rank approach. IEEE Trans Image Process 22(2):700–711
Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: Proceedings of the 13th European Conference on Computer Vision - ECCV 2014. Lecture Notes in Computer Science, vol 8692. Zurich, Switzerland, 6–12 September 2014, pp 184–199
Fan N (2009) Wavelet-based compressive super-resolution. In: 2009 Workshop on Applications of Computer Vision -WACV 2009. Snowbird, UT, USA, 7–8 December 2009, pp 1–6
Freedman G, Fattal R (2011) Image and video upscaling from local self-examples. ACM Trans Graph 30(2):1–11
Freeman WT, Pasztor EC (1999) Learning to estimate scenes from images. In: Kearns MS, Solla SA, Cohn DA (eds) Adv. Neural Information Processing Systems, vol. 11, MIT Press, Cambridge, pp 775–781
Freeman WT, Jones TR, Pasztor EC (2002) Example learning-based super-resolution. IEEE Comput Graphic Application 22(02):56–65
Glasner D, Bagon S, Irani M (2009) Super-resolution from a single image. IEEE Int Conf Comput Vision 30(2):349–356
Keys RG (1981) Cubic convolution interpolation for digital image processing. IEEE Trans Acoust Speech Signal Process 29(6):1153–1160
Lin Z, Shum H (2004) Fundamental limits of reconstruction-based super-resolution algorithms under local translation. IEEE Transac Pattern Anal Mach Intell 26(01):83–97
Lin Z, Chen M, Wu L, Ma Y (2009) The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices. UIUC technical report UILU-ENG-09-2215, November
Liu D, Wang Z, Wen B, Yang J, Han W, Huang T (2016) Robust single image super-resolution via deep networks with sparse prior. IEEE Transact Image Process. 25(7):1–14
Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A (2009) Non-local sparse models for image restoration. IEEE international conference computer vision. Pp 2272–2279
Mount DM, Arya S (1998) ANN: a library for approximate nearest neighbor searching. In: Proceedings of IEEE CGC Workshop on Computational Geometry, Providence, RI, USA 1998, pp 33–40
Nie F, Huang H, Cai X, Ding CH (2010) Efficient and robust feature selection via joint l2,1-norms minimization. In: Proceedings of the 23rd International Conference on Neural Information Processing Systems - NIPS’10. Vancouver, British Columbia, Canada, 6–9 December 2010, pp 1813–1821
Park S, Park M, Kang MG (2003) Super-resolution image reconstruction: a technical overview. IEEE Signal Process Mach 20(03):21–36
Ren CX, Dai DQ, Yan H (2012) Robust classification using l21-norm based regression model. Pattern Recogn 45(7):2708–2718
Romano Y, Isidoro JR, Milanfar P (2017) RAISR: rapid and accurate image super resolution. IEEE Transac Computat Imaging 3(1):110–125
Sen P, Darabi S (2009) Compressive image super-resolution. In: Proceedings of the 43rd Asilomar Conference on Signals, Systems and Computers -Asilomar'09. Pacific Grove, CA, USA, 1–4 November 2009, pp 1235–1242
Timofte R, De Smet V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution. In: Proceedings of the 2013 IEEE International Conference on Computer Vision - ICCV 2013. Sydney, Australia, 1–8 December 2013, pp 1920–1927
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Transact Image Process 13(4):600–612
Wright J, Ganesh A, Rao S, Ma Y (2009) Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization. Adv Neural Inf Proces Syst 87(4):1–44
Yang MC, Wang YCF (2013) A self-learning approach to single image super-resolution. IEEE Trans Multimedia 15(3):498–508
Yang CY, Yang MH (2013) Fast direct super-resolution by simple functions. In: Proceedings of the 2013 IEEE International Conference on Computer Vision -ICCV2013, vol 00. Sydney, NSW, Australia, 1–8 December 2013, pp 561–568
Yang J, Wright J, Huang T, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873
Yang CY, Huang JB, Yang MH (2010) Exploiting self-similarities for single frame super-resolution. In: Kimmel R, Klette R, Sugimoto A (eds) Computer Vision. Proceedings of the 10th Asian Conference on Computer Vision –ACCV 2010. Lecture Notes in Computer Science, vol 6494. Springer. Queenstown, New Zealand, 8–12 November 2010, pp 497–510
Yang CY, Ma C, Yang MH (2014) Single-image super-resolution: a benchmark. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision. Proceedings of the 13th European Conference on Computer Vision - ECCV 2014. Lecture Notes in Computer Science, vol 8692. Zurich, Switzerland, 6–12 September 2014, pp 372–386
Zeyde R, Elad M, Protter M (2010) On single image scale-up using sparse representations. In: Boissonnat JD et al (eds) Curves and Surfaces. Proceedings of the 7th international conference on Curves and Surfaces. Lecture Notes in Computer Science, vol 6920. Avignon, France, 24–30 June, 2010, pp 711–730
Zhang K, Gao X, Tao D, Li X (2012) Multiscale dictionary for single image super-resolution. In: Proceedings of the 2012 IEEE conference on Computer Vision and Pattern Recognition -CVPR '12, vol 00. Providence, RI USA, 16–21 June 2012, pp 1114–1121
Zhang K, Tao D, Gao X, Li X, Xiong X (2015) Learning multiple linear mappings for efficient single image super-resolution. IEEE Trans Image Process 24(3):846–861
Zhou F, Yuan T, Yang W, Liao Q (2015) Single image super-resolution based on compact KPCA coding and kernel regression. IEEE Signal Process Lett 22(3):336–340
Zontak M, Irani M (2011) Internal statistics of a single natural image. IEEE Conf Comput Vision Pattern Recog 42(7):977–984