Image Deblurring Based on an Improved CNN-Transformer Combination Network

8Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

Recently, using a CNN has been a common practice to restore blurry images due to its strong ability to learn feature information from large-scale datasets. However, CNNs essentially belong to local operations and have the defect of a limited receptive field, which reduces the naturalness of deblurring results. Moreover, CNN-based deblurring methods usually adopt many downsample operations, which hinder detail recovery. Fortunately, transformers focus on modeling the global features, so they can cooperate with CNNs to enlarge the receptive field and compensate for the details lost as well. In this paper, we propose an improved CNN-transformer combination network for deblurring, which adopts a coarse-to-fine architecture as the backbone. To extract the local features and global features simultaneously, the common methods are two blocks connected in parallel or cascaded. Different from these, we design a local-global feature combination block (LGFCB) with a new connecting structure to better use the extracted features. The LGFCB comprises multi-scale residual blocks (MRB) and a transformer block. In addition, we adopt a channel attention fusion block (CAFB) in the encoder path to integrate features. To improve the ability of feature representation, in the decoder path, we introduce a supervised attention block (SAB) operated on restoration images to refine features. Numerous experiments on GoPro and RealBlur datasets indicated that our model achieves remarkable accuracy and processing speed.

References Powered by Scopus

Going deeper with convolutions

39581Citations
N/AReaders
Get full text

End-to-End Object Detection with Transformers

9432Citations
N/AReaders
Get full text

Restormer: Efficient Transformer for High-Resolution Image Restoration

1790Citations
N/AReaders
Get full text

Cited by Powered by Scopus

An Improved Multimodal Medical Image Fusion Approach Using Intuitionistic Fuzzy Set and Intuitionistic Fuzzy Cross-Correlation

4Citations
N/AReaders
Get full text

CNB Net: A Two-Stage Approach for Effective Image Deblurring

1Citations
N/AReaders
Get full text

Artificial intelligence-powered image analysis: A paradigm shift in infectious disease detection

0Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Chen, X., Wan, Y., Wang, D., & Wang, Y. (2023). Image Deblurring Based on an Improved CNN-Transformer Combination Network. Applied Sciences (Switzerland), 13(1). https://doi.org/10.3390/app13010311

Readers' Seniority

Tooltip

Lecturer / Post doc 1

50%

Researcher 1

50%

Readers' Discipline

Tooltip

Engineering 2

67%

Computer Science 1

33%

Article Metrics

Tooltip
Mentions
News Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free