Item Infomation


Title: 
Deep unfolding multi-scale regularizer network for image denoising
Authors: 
Jingzhao, Xu
Mengke, Yuan
Dong-Ming, Yan
Issue Date: 
2023
Publisher: 
Springer
Abstract: 
Existing deep unfolding methods unroll an optimization algorithm with a fixed number of steps, and utilize convolutional neural networks (CNNs) to learn data-driven priors. However, their performance is limited for two main reasons. Firstly, priors learned in deep feature space need to be converted to the image space at each iteration step, which limits the depth of CNNs and prevents CNNs from exploiting contextual information. Secondly, existing methods only learn deep priors at the single full-resolution scale, so ignore the benefits of multi-scale context in dealing with high level noise. To address these issues, we explicitly consider the image denoising process in the deep feature space and propose the deep unfolding multi-scale regularizer network (DUMRN) for image denoising
Description: 
CC BY
URI: 
https://link.springer.com/article/10.1007/s41095-022-0277-5
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7311
Appears in Collections
OER - Công nghệ thông tin
ABSTRACTS VIEWS

31

FULLTEXT VIEWS

6

Files in This Item:

Thumbnail
  • s41095-022-0277-5.pdf
      Restricted Access
    • Size : 9,87 MB

    • Format : Adobe PDF