Abstract: We propose a super-resolution algorithm based on local adaptation. In the proposed algorithm, the mapping function from the low-resolution images to high-resolution image is estimated by adaptation. Moreover, the property of the high-resolution image is learned and incorporated in a regularization-based restoration. The proposed regularization function is used as a general directional total variation with adaptive weights. The adaptive weights of the directional total variation are estimated based on the property of the partially reconstructed high-resolution image. The regularization function can be thought as a linear combination of smoothness in different directions. The convexity conditions as well as the convergence conditions are studied for the proposed algorithm.
Omer, O. (2010). Learning-Based Image Super-Resolution with Directional Total Variation. The International Conference on Electrical Engineering, 7(7th International Conference on Electrical Engineering ICEENG 2010), 1-11. doi: 10.21608/iceeng.2010.33038
MLA
Osama. A. Omer. "Learning-Based Image Super-Resolution with Directional Total Variation". The International Conference on Electrical Engineering, 7, 7th International Conference on Electrical Engineering ICEENG 2010, 2010, 1-11. doi: 10.21608/iceeng.2010.33038
HARVARD
Omer, O. (2010). 'Learning-Based Image Super-Resolution with Directional Total Variation', The International Conference on Electrical Engineering, 7(7th International Conference on Electrical Engineering ICEENG 2010), pp. 1-11. doi: 10.21608/iceeng.2010.33038
VANCOUVER
Omer, O. Learning-Based Image Super-Resolution with Directional Total Variation. The International Conference on Electrical Engineering, 2010; 7(7th International Conference on Electrical Engineering ICEENG 2010): 1-11. doi: 10.21608/iceeng.2010.33038
)
View on SCiNiTO