Single Image Super-Resolution (SISR)

Single-image super-resolution (SISR) is a computer vision task that reconstructs a high-resolution (HR) image from a low-resolution (LR) image. It could be used in a variety of applications such as medical imaging, security, and surveillance imaging. The quality of the reconstructed HR image depends on how to extract and use the information from LR image. Since there are multiple HR images that can be downsampled to the same LR image and this is a one-to-many mapping relation to recover HR images from a LR image, SISR is an ill-posed and still challenging problem in the community.

In this project, we are developing techniques to reconstruct the HR image from the LR image. Our research is to address this problem from three directions. The first is to consider how to balance the reconstruction quality and time cost. The second is to investigate how to fuse multi-frequency information for HR image reconstruction. The third is to consider how simultaneously distill features in LR and HR space for SISR.

{{project.title}} {{tag[0]}} [{{link.name}}] 

{{img.label}}

Input-Output: {{project.io}}

Abstract: {{project.abstract}}

{{index+1}}