Single Image Super Resolution and Applications in Multispectral Imaging
Image super-resolution (SR), a process to enhance image resolution, has important applications in satellite imaging, high-definition television, medical imaging, and so on. Many existing approaches use multiple low-resolution (LR) images to recover one high-resolution (HR) image. We will present our latest research research results on single-image SR problem which recovers a high-quality HR image from solely one LR image without using a training data set. We solve the problem from image intensity function estimation perspective and assume that the image contains smooth and edge components that are modeled using different functions. We will also talk about the extension of the idea to pansharpening which fuses 3D low resolution multispectral images and a 2D high resolution panchromatic images for 3D high resolution multispectral images. The results involve collaboration with Richard Lartey (CWRU, USA), Liang-Jian Deng (UESTC, China) and Jocelyn Chanussot (Grenoble Institute of Technology, France).