Self-Verification in Image Denoising

11/01/2021
by   Huangxing Lin, et al.
0

We devise a new regularization, called self-verification, for image denoising. This regularization is formulated using a deep image prior learned by the network, rather than a traditional predefined prior. Specifically, we treat the output of the network as a “prior” that we denoise again after “re-noising”. The comparison between the again denoised image and its prior can be interpreted as a self-verification of the network's denoising ability. We demonstrate that self-verification encourages the network to capture low-level image statistics needed to restore the image. Based on this self-verification regularization, we further show that the network can learn to denoise even if it has not seen any clean images. This learning strategy is self-supervised, and we refer to it as Self-Verification Image Denoising (SVID). SVID can be seen as a mixture of learning-based methods and traditional model-based denoising methods, in which regularization is adaptively formulated using the output of the network. We show the application of SVID to various denoising tasks using only observed corrupted data. It can achieve the denoising performance close to supervised CNNs.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

research
05/09/2023

SwinIA: Self-Supervised Blind-Spot Image Denoising with Zero Convolutions

The essence of self-supervised image denoising is to restore the signal ...
research
08/03/2022

Decay2Distill: Leveraging spatial perturbation and regularization for self-supervised image denoising

Unpaired image denoising has achieved promising development over the las...
research
08/01/2023

Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review

The advent of deep learning has brought a revolutionary transformation t...
research
01/29/2019

Self-Supervised Deep Image Denoising

We describe techniques for training high-quality image denoising models ...
research
09/13/2022

PET image denoising based on denoising diffusion probabilistic models

Due to various physical degradation factors and limited counts received,...
research
10/08/2022

LW-ISP: A Lightweight Model with ISP and Deep Learning

The deep learning (DL)-based methods of low-level tasks have many advant...
research
03/17/2021

New Computational Techniques for a Faster Variation of BM3D Image Denoising

BM3D has been considered the standard for comparison in the image denois...

Please sign up or login with your details

Forgot password? Click here to reset