Multi-Frame Super-Resolution of High Frequency with Spatially Weighted Bilateral Total Variance Regularization

  • Lee, Oh-Young (School of Electrical Engineering, Korea University) ;
  • Park, Sae-Jin (School of Electrical Engineering, Korea University) ;
  • Kim, Jae-Woo (School of Electrical Engineering, Korea University) ;
  • Kim, Jong-Ok (School of Electrical Engineering, Korea University)
  • Received : 2014.01.15
  • Accepted : 2014.07.28
  • Published : 2014.10.31


Bayesian based Multi-Frame Super-Resolution (MF-SR) has been used as a popular and effective SR model. On the other hand, the texture region is not reconstructed sufficiently because it works on the spatial domain. In this study, the MF-SR method was extended to operate on the frequency domain to improve HF information as much as possible. For this, a spatially weighted bilateral total variation model was proposed as a regularization term for a Bayesian estimation. The experimental results showed that the proposed method can recover the texture region more realistically with reduced noise, compared to conventional methods.



Supported by : NIPA (National IT Industry Promotion Agency)


  1. S. Farsiu, M. Robinson, M. Elad, and P. Milanfar, "Fast and Robust Multi-Frame Super-Resolution," IEEE Trans. Image process., vol. 13, no.10, pp. 1327-1344, Oct. 2004. Article (CrossRef Link)
  2. A. Panagiotopoulou, V. Anastassopoulos, "Super-Resolution Image Reconstruction Techniques: tradeoffs between the data-fidelity and regularization terms," Inform. Fusion, 2008, vol.13, pp. 185-195, July. 2012. Article (CrossRef Link)
  3. Q. Yuan, L. Zhang, H. Shen, "Multi-Frame Super-Resolution Employing a Spatially Weighted Total Variation Model," IEEE Trans. Circuits and Systems for Video Technology, vol. 22, no.3, pp. 379-392, Mar. 2012. Article (CrossRef Link)
  4. X. Li and M. Orchad. "New Edge-Directed Interpolation," IEEE Trans. Image Process., vol. 10, pp. 1521-1527, Oct. 2001. Article (CrossRef Link)
  5. J.W. Hwang, H.S. Lee, "Adaptive Image Interpolation Based on Local Gradient Features," IEEE Signal Processing Letters, vol. 11, pp. 359-362, Mar.2004. Article (CrossRef Link)
  6. Takeda, H., Farsiu, S., and Milanfar, P., "Kernel Regression for Image Processing and Reconstruction", IEEE Trans. Image Process., pp. 349-366, Feb. 2007. Article (CrossRef Link)
  7. W.T. Freedman, T.R Jones, and E.C. Pasztor "Example-Based Super-Resolution," IEEE Computer Graphics and Applications, vol. 22, pp. 56-65, Mar. 2002. Article (CrossRef Link)
  8. S. Chen, H. Gong, and C. Li, "Super Resolution from a Single Image Based on Self-Similarity," IEEE Int. Conf. on Computational and Information Sciences, pp. 91-94, Oct. 2011. Article (CrossRef Link)
  9. D. Glasner, S. Bagon, and M.Irani, "Super-Resolution from a Single Image," 12th IEEE Int. Conf. on Computer Vision, pp. 349-356, Sept. 2009. Article (CrossRef Link)
  10. G. Freeman, and R. Fattal, "Image and Video Upscaling from Local Self-Examples," ACM Trans. on Graphics, vol. 30, Article No. 12, April. 2011. Article (CrossRef Link)
  11. C.Y Yand, J.B Huang, and M.H Yang, "Exploiting Self-Similarities for Single Frame Super-Resolution," Proc. of Asian Conf. on Computer Vision, pp. 497-510, Nov, 2010. Article (CrossRef Link)

Cited by

  1. Continuous digital zooming of asymmetric dual camera images using registration and variational image restoration pp.1573-0824, 2017,