Deng Liang-Jian, Guo Weihong, Huang Ting-Zhu
School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, Sichuan, 611731, P. R. China.
Department of Mathematics, Case Western Reserve University, Cleveland, OH, 44106, USA.
IEEE Trans Circuits Syst Video Technol. 2016 Nov;26(11):2001-2014. doi: 10.1109/TCSVT.2015.2475895. Epub 2015 Sep 2.
Image super-resolution, a process to enhance image resolution, has important applications in satellite imaging, high definition television, medical imaging, etc. Many existing approaches use multiple low-resolution images to recover one high-resolution image. In this paper, we present an iterative scheme to solve image super-resolution problems. It recovers a high quality high-resolution image from solely one low-resolution image without using a training data set. We solve the problem from image intensity function estimation perspective and assume the image contains smooth and edge components. We model the smooth components of an image using a thin-plate reproducing kernel Hilbert space (RKHS) and the edges using approximated Heaviside functions. The proposed method is applied to image patches, aiming to reduce computation and storage. Visual and quantitative comparisons with some competitive approaches show the effectiveness of the proposed method.
图像超分辨率是一种提高图像分辨率的过程，在卫星成像、高清电视、医学成像等领域有着重要应用。许多现有方法使用多个低分辨率图像来恢复一个高分辨率图像。在本文中，我们提出了一种迭代方案来解决图像超分辨率问题。它仅从一个低分辨率图像中恢复高质量的高分辨率图像，而无需使用训练数据集。我们从图像强度函数估计的角度解决该问题，并假设图像包含平滑和边缘成分。我们使用薄板再生核希尔伯特空间（RKHS）对图像的平滑成分进行建模，并使用近似的海维赛德函数对边缘进行建模。所提出的方法应用于图像块，旨在减少计算量和存储量。与一些有竞争力的方法进行的视觉和定量比较表明了该方法的有效性。
