ResDiff: Combining CNN and Diffusion Model for Image Super-resolution

Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content. Therefore, we present ResDiff, a novel Diffusion Probabilistic Model based on Residual structure for Single Image Super-Resolution (SISR). ResDiff utilizes a combination of a CNN, which restores primary low-frequency components, and a DPM, which predicts the residual between the ground-truth image and the CNN predicted image. In contrast to the common diffusion-based methods that directly use LR space to guide the noise towards HR space, ResDiff utilizes the CNN’s initial prediction to direct the noise towards the…

• SU
  Shandong University
• GO
  Government of Jiangsu Province
• LU
  Linyi University
• NK
  National Key Research and Development Program of China

  Awards: BE2021093, 2022YFB4500602