基于对偶字典学习的图像超分辨技术研究

Image super resolution based on couple dictionary learning

提出一种基于对偶字典学习的图像超分辨方法,通过稀疏重建的方法得到重建的图像,对偶字典通过稀疏表示将低分辨图像和高分辨图像联系起来。在稀疏表示过程中,低分辨图像在低分辨字典上的稀疏表示能够很好地提高对应的高分辨图像在高分辨字典上的稀疏表示效果。将字典的学习建模为包含l1范数优化问题的双层最优化问题,采用隐微分法计算随机梯度下降的期望梯度。仿真实验结果表明,该方法能够达到和联合字典学习方法相同的速度和质量,同时,在实际应用中可以通过神经网络模型学习方法提高算法的速度。与现有的算法比较,表明了该算法的有效性。

A novel coupled dictionary training method for single image super resolution based on patch-wise sparse recovery is proposed,where the learned couple dictionaries relate the low and high-resolution image patch spaces via sparse representation.The learning process enforces that the sparse representation of a low-resolution image patch in terms of the low-resolution dictionary can well reconstruct its underlying high-resolution image patch with the dictionary in the high-resolution image patch space.The learning problem is modeled as a bilevel optimization problem,where the optimization includes an l1 norm minimization problem in its constraints.Implicit differentiation is employed to calculate the desired gradient for stochastic gradient descent.Coupled dictionary learning method can outperform the existing joint dictionary training method both quantitatively and qualitatively.Extensive experimental comparisons with state-of-the-art super-resolution algorithms validate the effectiveness of our proposed approach.