Super-Resolution Using Sub-Band Self-Similarity

详细信息    查看全文

• 作者：Abhishek Singh (17)
  Narendra Ahuja (17)
  
  17. University of Illinois at Urbana-Champaign ; Champaign ; USA
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9004
• 期：1
• 页码：552-568
• 全文大小：7,971 KB
• 参考文献：1. Freeman, W., Pasztor, E.: Learning low-level vision. In: ICCV (1999)
  2. Yang, J, Wright, J, Huang, T, Ma, Y (2010) Image super-resolution via sparse representation. IEEE Trans. Image Proc. 98: pp. 1031-1044
  3. Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution as sparse representation of raw image patches. In: CVPR (2008)
  4. Sun, J., Zheng, N.N., Tao, H., Shum, H.Y.: Image hallucination with primal sketch priors. In: CVPR (2003)
  5. Yeung, D.Y., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: CVPR(2004)
  6. Glasner, D., Bagon, S., Irani, M.: Super-resolution from a single image. In: ICCV (2009)
  7. Freeman, WT, Pasztor, EC (2000) Learning low-level vision. IJCV 40: pp. 25-47 CrossRef
  8. Wang, S., Zhang, D., Liang, Y., Pan, Q.: Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. In: CVPR (2012)
  9. Yang, C.Y., Yang, M.H.: Fast direct super-resolution by simple functions. In: ICCV (2013)
  10. Ebrahimi, M, Vrscay, ER Solving the inverse problem of image zooming using 鈥淪elf-Examples鈥? In: Kamel, MS, Campilho, A eds. (2007) Image Analysis and Recognition. Springer, Heidelberg, pp. 117-130 CrossRef
  11. Freedman, G, Fattal, R (2010) Image and video upscaling from local self-examples. ACM Trans. Graph. 28: pp. 1-10
  12. Yang, C-Y, Huang, J-B, Yang, M-H Exploiting self-similarities for single frame super-resolution. In: Kimmel, R, Klette, R, Sugimoto, A eds. (2011) Computer Vision 鈥?ACCV 2010. Springer, Heidelberg, pp. 497-510 CrossRef
  13. Singh, A., Ahuja, N.: Sub-band energy constraints for self-similarity based super-resolution. In: ICPR (2014)
  14. Singh, A., Porikli, F., Ahuja, N.: Super-resolving noisy images. In: CVPR (2014)
  15. Barnsley, M (1988) Fractals Everywhere. Academic Press Professional, Inc., San Diego
  16. Polidori, E., luc Dugelay, J.: Zooming using iterated function systems (1995)
  17. Zontak, M., Irani, M.: Internal statistics of a single natural image. In: CVPR (2011)
  18. Freeman, W, Jones, T, Pasztor, E (2002) Example-based super-resolution. Comput. Graph. Appl. 22: pp. 56-65 CrossRef
  19. Yang, J, Wang, Z, Lin, Z, Cohen, S, Huang, T (2012) Coupled dictionary training for image super-resolution. IEEE Trans. Image Proc. 21: pp. 3467-3478 CrossRef
  20. Yang, J., Lin, Z., Cohen, S.: Fast image super-resolution based on in-place example regression. In: CVPR (2013)
  21. Fattal, R (2007) Image upsampling via imposed edge statistics. ACM Trans. Graph. 26: pp. 95 CrossRef
  22. Sun, J, Sun, J, Xu, Z, Shum, HY (2011) Gradient profile prior and its applications in image super-resolution and enhancement. IEEE Trans. Image Proc. 20: pp. 1529-1542 CrossRef
  23. Sun, J., Sun, J., Xu, Z., Shum, H.Y.: Image super-resolution using gradient profile prior. In: CVPR (2008)
  24. Jiji, CV, Chaudhuri, S (2006) Single-frame image super-resolution through contourlet learning. EURASIP J. Appl. Signal Process. 2006: pp. 235 CrossRef
  25. Gajjar, P, Joshi, M (2010) New learning based super-resolution: Use of dwt and igmrf prior. IEEE Trans. Image Proc. 19: pp. 1201-1213 CrossRef
  26. Sun, J., Zhu, J., Tappen, M.: Context-constrained hallucination for image super-resolution. In: CVPR (2010)
  27. HaCohen, Y., Fattal, R., Lischinski, D.: Image upsampling via texture hallucination. In: ICCP (2010)
  28. Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: CVPR (2005)
  29. Simoncelli, E., Freeman, W.: The steerable pyramid: a flexible architecture for multi-scale derivative computation. In: ICIP (1995)
  30. Simoncelli, E, Freeman, W, Adelson, E, Heeger, D (1992) Shiftable multiscale transforms. IEEE Trans. Info. Theory 38: pp. 587-607 CrossRef
  31. Do, M, Vetterli, M (2005) The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans. Image Proc. 14: pp. 2091-2106 CrossRef
  32. Irani, M, Peleg, S (1991) Improving resolution by image registration. CVGIP 53: pp. 231-239
  33. Kim, K, Kwon, Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE TPAMI 32: pp. 1127-1133 CrossRef
  34. Shan, Q, Li, Z, Jia, J, Tang, CK (2008) Fast image/video upsampling. ACM Trans. Graph. 27: pp. 1-7
  35. Wang, Z, Bovik, A, Sheikh, H, Simoncelli, E (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Proc. 13: pp. 600-612 CrossRef
  
• 作者单位：Computer Vision -- ACCV 2014
• 丛书名：978-3-319-16807-4
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

A popular approach for single image super-resolution (SR) is to use scaled down versions of the given image to build an internal training dictionary of pairs of low resolution (LR) and high resolution (HR) image patches, which is then used to predict the HR image. This self-similarity approach has the advantage of not requiring a separate external training database. However, due to their limited size, internal dictionaries are often inadequate for finding good matches for patches containing complex structures such as textures. Furthermore, the quality of matches found are quite sensitive to factors like patch size (larger patches contain structures of greater complexity and may be difficult to match), and dimensions of the given image (smaller images yield smaller internal dictionaries). In this paper we propose a self-similarity based SR algorithm that addresses the abovementioned drawbacks. Instead of seeking similar patches directly in the image domain, we use the self-similarity principle independently on each of a set of different sub-band images, obtained using a bank of orientation selective band-pass filters. Therefore, we allow the different directional frequency components of a patch to find matches independently, which may be in different image locations. Essentially, we decompose local image structure into component patches defined by different sub-bands, with the following advantages: (1) The sub-band image patches are simpler and therefore easier to find matches, than for the more complex textural patches from the original image. (2) The size of the dictionary defined by patches from the sub-band images is exponential in the number of sub-bands used, thus increasing the effective size of the internal dictionary. (3) As a result, our algorithm exhibits a greater degree of invariance to parameters like patch size and the dimensions of the LR image. We demonstrate these advantages and show that our results are richer in textural content and appear more natural than several state-of-the-art methods.