SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models

by   Haoying Li, et al.

Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images. Recently, learning-based SISR methods have greatly outperformed traditional ones, while suffering from over-smoothing, mode collapse or large model footprint issues for PSNR-oriented, GAN-driven and flow-based methods respectively. To solve these problems, we propose a novel single image super-resolution diffusion probabilistic model (SRDiff), which is the first diffusion-based model for SISR. SRDiff is optimized with a variant of the variational bound on the data likelihood and can provide diverse and realistic SR predictions by gradually transforming the Gaussian noise into a super-resolution (SR) image conditioned on an LR input through a Markov chain. In addition, we introduce residual prediction to the whole framework to speed up convergence. Our extensive experiments on facial and general benchmarks (CelebA and DIV2K datasets) show that 1) SRDiff can generate diverse SR results in rich details with state-of-the-art performance, given only one LR input; 2) SRDiff is easy to train with a small footprint; and 3) SRDiff can perform flexible image manipulation including latent space interpolation and content fusion.


page 1

page 4

page 5

page 7


Fast single image super-resolution based on sigmoid transformation

Single image super-resolution aims to generate a high-resolution image f...

Real-World Single Image Super-Resolution: A Brief Review

Single image super-resolution (SISR), which aims to reconstruct a high-r...

D2C-SR: A Divergence to Convergence Approach for Image Super-Resolution

In this paper, we present D2C-SR, a novel framework for the task of imag...

Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network

Normalizing flow models have been used successfully for generative image...

Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning

Recently, machine learning based single image super resolution (SR) appr...

Image Super-Resolution via Sparse Bayesian Modeling of Natural Images

Image super-resolution (SR) is one of the long-standing and active topic...

Diverse super-resolution with pretrained deep hiererarchical VAEs

Image super-resolution is a one-to-many problem, but most deep-learning ...