PROJECT TITLE :

Fast Image Super-Resolution via Local Adaptive Gradient Field Sharpening Transform - 2018

ABSTRACT:

This Project proposes a single-image super-resolution theme by introducing a gradient field sharpening rework that converts the blurry gradient field of upsampled low-resolution (LR) image to a a lot of sharper gradient field of original high-resolution (HR) image. Totally different from the existing methods that need to work out the full gradient profile structure and locate the sting points, we tend to derive a replacement approach that sharpens the gradient field adaptively solely based mostly on the pixels during a small neighborhood. To maintain image contrast, image gradient is adaptively scaled to keep the integral of gradient field stable. Finally, the HR image is reconstructed by fusing the LR image with the sharpened HR gradient field. Experimental results demonstrate that the proposed algorithm can generate a lot of accurate gradient field and manufacture super-resolved images with better objective and visual qualities. Another advantage is that the proposed gradient sharpening transform is very fast and appropriate for low-complexity applications.