High Quality Artifact-free Super-resolution

Wei Zhang, Wai-Kuen Cham

The proposed super-resolution framework


Blurring and jaggy artifacts are the primal culprits that plague the current super-resolution techniques. In this paper, we propose a simple but effective approach which is capable of producing pleasant high-resolution (HR) image with rare artifacts from a single low-resolution input. Specifically, we first magnify the low-resolution (LR) image to the desired resolution through structure adaptive interpolation which can avoid jaggies effectively. Then a salient edge directed deblurring scheme is introduced to remove the blurriness of the magnified image. Unlike previous work, we advocate solving the deblurring problem in an efficient manner with the aid of little user intervention. Our study shows that the blurring kernel can be estimated fairly well from the salient edges selected with user-drawn stroke based on a parametric edge model. Experiments are conducted to validate the effectiveness of the proposed method.


Wei Zhang and Wai-Kuen Cham. High Quality Artifact-free Super-resolution. IEEE International Conference on Image Processing (ICIP). Hong Kong, Sep. 2010.

Experimental Results






  • [SAI] X. Zhang and X. Wu. Image interpolation by adaptive 2D autoregressive modeling and soft-decision estimation. IEEE Transactions on Image Processing (T-IP), vol. 17, pp.887-896, 2008.
  • [Ma et al.] L. Ma, Y. Zhang, Y. Lu, F. Wu, and D. Zhao. Three-tiered network model for image hallucination. Proc. IEEE International Conference on Image Processing (ICIP) 2008.
  • [Dai et al.] S. Dai, M. Han, W. Xu, Y. Wu, Y. Gong, and A. Katsaggelos. SoftCuts: a soft edge smoothness prior for color image super-resolution. IEEE Transactions on Image Processing (T-IP), vol. 18, pp. 969-981, 2009.

Back to Home