IDTransformer: Infrared image denoising method based on convolutional transposed self-attention
Image denoising is a quintessential challenge in computer vision, intending to produce high-quality, clean images from degraded, noisy counterparts. Infrared imaging holds a pivotal position across many research domains, attributed to its inherent benefits such as concealment and noninvasiveness. De...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824011256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553823778209792 |
|---|---|
| author | Zhengwei Shen Feiwei Qin Ruiquan Ge Changmiao Wang Kai Zhang Jie Huang |
| author_facet | Zhengwei Shen Feiwei Qin Ruiquan Ge Changmiao Wang Kai Zhang Jie Huang |
| author_sort | Zhengwei Shen |
| collection | DOAJ |
| description | Image denoising is a quintessential challenge in computer vision, intending to produce high-quality, clean images from degraded, noisy counterparts. Infrared imaging holds a pivotal position across many research domains, attributed to its inherent benefits such as concealment and noninvasiveness. Despite these advantages, infrared images are often plagued by hardware-related imperfections resulting in poor contrast, diminished quality, and noise contamination. Extracting and characterizing features amidst these unique feature patterns in infrared imagery are taxing tasks. To surmount these obstacles, we introduce the Infrared image Denoising Transformer (IDTransformer), encapsulated in a symmetrical encoder–decoder architecture. Central to our approach is the Convolutional Transposed Self-Attention Block (CTSAB), which is ingeniously conceived to capture long-range dependencies via channel-wise self-attention, while simultaneously encapsulating local context through depth-wise convolution. In addition, we refine the conventional feed-forward network by integrating Convolutional Gated Linear Units (CGLU) and deploy the Channel Coordinate Attention Block (CCAB) during the feature fusion phase to dynamically apportion weights across the feature map, thereby facilitating a more nuanced representation of pattern features endemic to infrared images. Through rigorous experimentation, we establish that our IDTransformer attains superior visual enhancement across five infrared image datasets, compared with the state-of-the-art methods. The source codes are available at https://github.com/szw811/IDTransformer. |
| format | Article |
| id | doaj-art-745c450d4d5545248610665b18cbc389 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-745c450d4d5545248610665b18cbc3892025-01-09T06:13:18ZengElsevierAlexandria Engineering Journal1110-01682025-01-01110310321IDTransformer: Infrared image denoising method based on convolutional transposed self-attentionZhengwei Shen0Feiwei Qin1Ruiquan Ge2Changmiao Wang3Kai Zhang4Jie Huang5School of Computer Science and Technology, Hangzhou Dianzi University, ChinaSchool of Computer Science and Technology, Hangzhou Dianzi University, China; Corresponding author.School of Computer Science and Technology, Hangzhou Dianzi University, ChinaShenzhen Research Institute of Big Data, ChinaComputer Vision Lab, ETH Zurich, Zurich, SwitzerlandSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, ChinaImage denoising is a quintessential challenge in computer vision, intending to produce high-quality, clean images from degraded, noisy counterparts. Infrared imaging holds a pivotal position across many research domains, attributed to its inherent benefits such as concealment and noninvasiveness. Despite these advantages, infrared images are often plagued by hardware-related imperfections resulting in poor contrast, diminished quality, and noise contamination. Extracting and characterizing features amidst these unique feature patterns in infrared imagery are taxing tasks. To surmount these obstacles, we introduce the Infrared image Denoising Transformer (IDTransformer), encapsulated in a symmetrical encoder–decoder architecture. Central to our approach is the Convolutional Transposed Self-Attention Block (CTSAB), which is ingeniously conceived to capture long-range dependencies via channel-wise self-attention, while simultaneously encapsulating local context through depth-wise convolution. In addition, we refine the conventional feed-forward network by integrating Convolutional Gated Linear Units (CGLU) and deploy the Channel Coordinate Attention Block (CCAB) during the feature fusion phase to dynamically apportion weights across the feature map, thereby facilitating a more nuanced representation of pattern features endemic to infrared images. Through rigorous experimentation, we establish that our IDTransformer attains superior visual enhancement across five infrared image datasets, compared with the state-of-the-art methods. The source codes are available at https://github.com/szw811/IDTransformer.http://www.sciencedirect.com/science/article/pii/S1110016824011256Image denoisingInfrared imageSelf-attentionFeature fusion |
| spellingShingle | Zhengwei Shen Feiwei Qin Ruiquan Ge Changmiao Wang Kai Zhang Jie Huang IDTransformer: Infrared image denoising method based on convolutional transposed self-attention Alexandria Engineering Journal Image denoising Infrared image Self-attention Feature fusion |
| title | IDTransformer: Infrared image denoising method based on convolutional transposed self-attention |
| title_full | IDTransformer: Infrared image denoising method based on convolutional transposed self-attention |
| title_fullStr | IDTransformer: Infrared image denoising method based on convolutional transposed self-attention |
| title_full_unstemmed | IDTransformer: Infrared image denoising method based on convolutional transposed self-attention |
| title_short | IDTransformer: Infrared image denoising method based on convolutional transposed self-attention |
| title_sort | idtransformer infrared image denoising method based on convolutional transposed self attention |
| topic | Image denoising Infrared image Self-attention Feature fusion |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824011256 |
| work_keys_str_mv | AT zhengweishen idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention AT feiweiqin idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention AT ruiquange idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention AT changmiaowang idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention AT kaizhang idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention AT jiehuang idtransformerinfraredimagedenoisingmethodbasedonconvolutionaltransposedselfattention |