מידע ביבליוגרפי
| כותר: |
Image rain removal network based on checkerboard transformer and CNN hybrid mechanism. |
| Authors: |
Yang Y; College of Computer Science and Technolog, Civil Aviation University of China, Tianjin, China., Lin J; University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan, China., Dai X; College of Computer Science and Technolog, Civil Aviation University of China, Tianjin, China., Zhang Z; University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan, China., Zhang S; School of Computing, North China Institute of Science and Technology, Langfang, China., Chen Y; College of Aeronautical Engineering Institute, Civil Aviation University of China, Tianjin, China., Kong G; School of Electrical Engineering, Yanshan University, Qinhuangdao, China., Li X; Sinopec Qilu Petrochemical Company, Zibo, China. |
| Source: |
PloS one [PLoS One] 2025 May 16; Vol. 20 (5), pp. e0322011. Date of Electronic Publication: 2025 May 16 (Print Publication: 2025). |
| Publication Type: |
Journal Article |
| שפה: |
English |
| Journal Info: |
Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE |
| Imprint Name(s): |
Original Publication: San Francisco, CA : Public Library of Science |
| MeSH Terms: |
Neural Networks, Computer* , Rain* , Image Processing, Computer-Assisted*/methods, Algorithms |
| Abstract: |
Competing Interests: No author has conflicting interests.
In this paper, a novel hybrid network called ChessFormer is proposed for the single image de-rain task. The network seamlessly integrates the advantages of Transformer and fitted neural network (CNN) in a checkerboard architecture, fully utilizing the global modeling capability of Transformer and the local feature extraction efficiency of CNN.ChessFormer adopts a multilevel feature extraction and progressive feature fusion strategy to efficiently achieve the rain line while preserving the We design a multidimensional transposed attention (MSTA), which enhances the network fusion for different rain patterns and mechanism image textures by combining self-attention with gated phase operation. In addition, the efficient architecture ensures full integration of features across dimensions and codecs. Experimental results show that ChessFormer outperforms existing methods in terms of quantitative metrics and visual quality on multiple benchmark datasets, achieving state-of-the-art performance with fewer parameters.
(Copyright: © 2025 Yang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
| References: |
IEEE Trans Pattern Anal Mach Intell. 2023 Aug;45(8):9454-9468. (PMID: 37022836)
IEEE Trans Neural Netw Learn Syst. 2020 Jun;31(6):1794-1807. (PMID: 31329133)
IEEE Trans Pattern Anal Mach Intell. 2023 Jun;45(6):6896-6908. (PMID: 32750802)
IEEE Trans Pattern Anal Mach Intell. 2017 Apr;39(4):640-651. (PMID: 27244717)
IEEE Trans Image Process. 2024;33:69-81. (PMID: 38032791)
IEEE Trans Neural Netw Learn Syst. 2023 Jul;34(7):3594-3608. (PMID: 34559666)
IEEE Trans Pattern Anal Mach Intell. 2020 Jun;42(6):1377-1393. (PMID: 30703011)
IEEE Trans Pattern Anal Mach Intell. 2022 Oct;44(10):7112-7127. (PMID: 34232869)
IEEE Trans Image Process. 2017 Jun;26(6):2944-2956. (PMID: 28410108) |
| Entry Date(s): |
Date Created: 20250516 Date Completed: 20250516 Latest Revision: 20250518 |
| Update Code: |
20250519 |
| PubMed Central ID: |
PMC12084057 |
| DOI: |
10.1371/journal.pone.0322011 |
| PMID: |
40378370 |
| Database: |
MEDLINE |
|
Full text is not displayed to guests. |
Login for full access.
|