Learning the Degradation Distribution for Blind Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Zhengxiong, Huang, Yan, Li, Shang, Wang, Liang, Tan, Tieniu
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911757077839872
author Luo, Zhengxiong
Huang, Yan
Li, Shang
Wang, Liang
Tan, Tieniu
author_facet Luo, Zhengxiong
Huang, Yan
Li, Shang
Wang, Liang
Tan, Tieniu
contents Synthetic high-resolution (HR) \& low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the following SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation $\mathbf{D}$ as a random variable, and learns its distribution by modeling the mapping from a priori random variable $\mathbf{z}$ to $\mathbf{D}$. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. The source codes are released at \url{git@github.com:greatlog/UnpairedSR.git}.
format Preprint
id arxiv_https___arxiv_org_abs_2203_04962
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Learning the Degradation Distribution for Blind Image Super-Resolution
Luo, Zhengxiong
Huang, Yan
Li, Shang
Wang, Liang
Tan, Tieniu
Image and Video Processing
Computer Vision and Pattern Recognition
Synthetic high-resolution (HR) \& low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the following SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation $\mathbf{D}$ as a random variable, and learns its distribution by modeling the mapping from a priori random variable $\mathbf{z}$ to $\mathbf{D}$. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. The source codes are released at \url{git@github.com:greatlog/UnpairedSR.git}.
title Learning the Degradation Distribution for Blind Image Super-Resolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2203.04962