一种利用改进深度图像先验构建的图像降噪模型

徐少平; 李芬; 陈孝国; 陈晓军; 江顺亮

doi:10.12263/DZXB.20211323

您当前的位置：

首页 >

文章列表页 >

一种利用改进深度图像先验构建的图像降噪模型

学术论文 | 更新时间：2025-12-08

- 一种利用改进深度图像先验构建的图像降噪模型
- An Image Denoising Model Using the Improved Deep Image Prior
- 电子学报 2022年50卷第7期页码：1573-1578
- 作者机构：
  
  南昌大学数学与计算机学院，江西南昌 330031
- 作者简介：
  
  [ "徐少平男，1976年5月出生于江西省九江市．博士，南昌大学数学与计算机学院计算机科学与技术系教授，博士生导师.主要研究方向为图形图像处理、机器视觉、虚拟手术仿真等．" ]
  [ "李芬女，1995年8月出生于江西省南昌市. 现为南昌大学硕士研究生，主要研究方向为图像处理与计算机视觉．E-mail: 411014519034@email.ncu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62162043;62162042;62102174)
- DOI：10.12263/DZXB.20211323
  中图分类号： TP391.4
- 收稿：2021-09-28，
  
  修回：2022-03-06，
  
  纸质出版：2022-07-25
- 稿件说明：
移动端阅览
徐少平,李芬,陈孝国等.一种利用改进深度图像先验构建的图像降噪模型[J].电子学报,2022,50(07):1573-1578.

XU Shao-ping,LI Fen,CHEN Xiao-guo,et al.An Image Denoising Model Using the Improved Deep Image Prior[J].ACTA ELECTRONICA SINICA,2022,50(07):1573-1578.
徐少平,李芬,陈孝国等.一种利用改进深度图像先验构建的图像降噪模型[J].电子学报,2022,50(07):1573-1578. DOI： 10.12263/DZXB.20211323.

XU Shao-ping,LI Fen,CHEN Xiao-guo,et al.An Image Denoising Model Using the Improved Deep Image Prior[J].ACTA ELECTRONICA SINICA,2022,50(07):1573-1578. DOI： 10.12263/DZXB.20211323.

摘要

为进一步提高深度图像先验（Deep Image Prior，DIP）降噪模型的降噪效果和执行效率，从网络结构、网络输入和Loss函数三个方面对其进行改进从而获得了一种改进的深度图像先验（Improved Deep Image Prior，IDIP）降噪模型.具体地，在网络结构方面，通过新增非线性特征传递路径的方法将原DIP模型编码器-解码器（encoder-decoder）架构中相同尺度特征层之间所采用的简单连接改进为复杂连接，有利于特征信息调制与传递从而提高神经网络的非线性映射能力；在网络输入方面，用已具有较高图像质量的初步降噪图像替换随机张量作为网络输入向网络模型提供更为丰富的信息，有利于加快网络收敛速度进而提高执行效率；在Loss函数方面，在原噪声图像的基础上新增初步降噪图像作为第二目标图像，有利于提高Loss函数的导向能力从而提高降噪效果.实验结果表明：所提出的IDIP降噪模型在各噪声水平值下的降噪性能和执行效率均显著优于原DIP模型；与现有的主流降噪方法相比，IDIP降噪模型也具有更好的降噪效果.

Abstract

To further improve the execution efficiency and denoising effect of the deep image prior(DIP) denoising model

an improved deep image prior(IDIP) denoising model was proposed by improving the original DIP from three aspects

network architecture

network input

and Loss function. Specifically

considering the network architecture

the simple connection adopted in the encoder-decoder backbone network was promoted with complex connection by adding nonlinear features transferring path

which brings benefit to the information modulation and transmission of features between encoder and decoder at the same level. In aspect of the network input

the random tensor was replaced by the preliminary denoised image with better image quality

and the preliminary denoised image can provide more abundant information to the network model

accelerating the convergence speed of network and improving the execution efficiency. Regarding the Loss function

the preliminary denoised image was added as the second target image to improve the guidance ability of the loss function

improving denoising effect significantly. Extensive experiments show that

the proposed IDIP denoising model significantly outperforms original one at various noise levels in terms of denoising effect and execution efficiency

and it also has a better performance than other state-of-the-art methods with regard to denoising effect.

关键词

Keywords

references

LI J X , GUO X B , LU G M , et al . DRPL: Deep regression pair learning for multi-focus image fusion [J]. IEEE Transactions on Image Processing , 2020 , 29 ( 3 ): 4816 - 4831 .

WANG C H , HOU B C , SHI J , et al . Uniformity evaluation of temperature field in an oven based on image processing [J]. IEEE Access , 2020 , 8 ( 1 ): 10243 - 10253 .

ZHANG K , ZUO W M , CHEN Y J , et al . Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising [J]. IEEE Transactions on Image Processing , 2017 , 26 ( 7 ): 3142 - 3155 .

ZHANG K , ZUO W M , ZHANG L . FFDNet: Toward a fast and flexible solution for CNN based image denoising [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 9 ): 4608 - 4622 .

YUE Z S , YONG H W , ZHAO Q , et al . Variational denoising network: Toward blind noise modeling and removal [C]// Advances in Neural Information Processing Systems . Vancouver : Neural Information Processing Systems Foundation , 2019 : 1 - 12 .

DMITRY U , VEDALDI A , VICTOR L . Deep image prior [J]. International Journal of Computer Vision , 2020 , 128 ( 8 ): 1867 - 1888 .

VIGNESH R , BALAMURALI M , SHARATH M S , et al . Deep network for capacitive ECG denoising [C]// Medical Measurements and Applications . Istanbul : IEEE , 2019 : 1 - 6 .

DABOV K , FOI A , KATKOVNIK V , et al . Image denoising by sparse 3-D transform-domain collaborative filtering [J]. IEEE Transactions on Image Processing , 2007 , 16 ( 8 ): 2080 - 2095 .

FU J , DONG J B , ZHAO F . A deep learning reconstruction framework for differential phase-contrast computed tomography with incomplete data [J]. IEEE Transactions on Image Processing , 2020 , 29 ( 1 ): 2190 - 2202 .

ARBELAEZ P , MAIRE M , FOWLKES C , et al . Contour detection and hierarchical image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 , 33 ( 5 ): 898 - 916 .

DONG W S , ZHANG L , SHI G M , et al . Nonlocally centralized sparse representation for image restoration [J]. IEEE Transactions on Image Processing , 2013 , 22 ( 4 ): 1620 - 1630 .

GU S H , ZHANG L , ZUO W M , et al . Weighted nuclear norm minimization with application to image denoising [C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Columbus : IEEE Computer Society , 2014 : 2862 - 2869 .

SOH J W , CHO S , CHO N I . Meta-transfer learning for zero-shot super-resolution [C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Seattle : IEEE Computer Society , 2020 : 3513 - 3522 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

双通道深度图像先验降噪模型

基于图拉普拉斯正则化的PET图像核重建方法