BCDA-Net: A Bottleneck-Free Channel Dual-Path Aggregation Network for Infrared Image Destriping.
Saved in:
| Title: | BCDA-Net: A Bottleneck-Free Channel Dual-Path Aggregation Network for Infrared Image Destriping. |
|---|---|
| Authors: | Chen, Lingzhi1,2 (AUTHOR), Dong, Feng1,2 (AUTHOR), Huang, Lingfeng1 (AUTHOR), Fu, Yutian1,2 (AUTHOR) yutianfu@mail.sitp.ac.cn |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 9, p1321. 24p. |
| Subjects: | Image denoising, Image reconstruction, Infrared imaging, Deep learning, Remote sensing, Noise control |
| Abstract: | Highlights: What are the main findings? We developed BCDA-Net, a novel architecture that integrates a Dual-Path Channel Down-sampling (DCD) module and a Bottleneck-Free Aggregation Strategy (BFAS) to structurally block the propagation of low-resolution noise. By further coupling a Context-Guided Stripe Attention Block (CGSAB) with a Cascaded Dense Feature Aggregation (CDFA) module, the network achieves state-of-the-art visual quality and quantitative metrics on both simulated and real-world infrared datasets. What are the implications of the main findings? The bottleneck-free design successfully overcomes the traditional trade-off between effective denoising and detail preservation by structurally blocking the propagation of low-resolution aliasing artifacts. This network provides a highly robust preprocessing framework for wide-swath high-resolution infrared remote sensing, significantly enhancing the reliability of subsequent downstream applications. The inherent non-uniformity of Infrared Focal Plane Arrays (IRFPA) inevitably results in stripe noise, which severely degrades image quality and hinders downstream applications. Existing deep learning methods often struggle to strike a balance between effective denoising and the preservation of fine thermal textures. To address this issue, we propose a Bottleneck-free Channel Dual-path Aggregation Network (BCDA-Net) based on a "Perception-Reconstruction" design principle. In the perception stage, the network jointly employs the Dual-Path Channel Down-sampling (DCD) module and the Context-Guided Stripe Attention Block (CGSAB). The DCD module utilizes a channel split strategy to simultaneously extract semantic features and preserve high-frequency textures, while the CGSAB performs global context modeling on these features to precisely perceive and locate global stripe noise patterns. In the reconstruction stage, we integrate the Cascaded Dense Feature Aggregation (CDFA) module with a Bottleneck-Free Aggregation Strategy (BFAS). The CDFA utilizes the perceived information to densely aggregate features and progressively reconstruct clean image details, whereas the BFAS structurally blocks the propagation of low-resolution noise during decoding, effectively mitigating aliasing artifacts induced by deep feature upsampling. Together, these components form a complete closed loop from accurate noise perception to high-fidelity reconstruction. Extensive experiments on public and real-world datasets demonstrate that BCDA-Net maximally preserves image details while removing non-uniform stripe noise. Both objective metrics and subjective visual quality outperform existing state-of-the-art methods. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? We developed BCDA-Net, a novel architecture that integrates a Dual-Path Channel Down-sampling (DCD) module and a Bottleneck-Free Aggregation Strategy (BFAS) to structurally block the propagation of low-resolution noise. By further coupling a Context-Guided Stripe Attention Block (CGSAB) with a Cascaded Dense Feature Aggregation (CDFA) module, the network achieves state-of-the-art visual quality and quantitative metrics on both simulated and real-world infrared datasets. What are the implications of the main findings? The bottleneck-free design successfully overcomes the traditional trade-off between effective denoising and detail preservation by structurally blocking the propagation of low-resolution aliasing artifacts. This network provides a highly robust preprocessing framework for wide-swath high-resolution infrared remote sensing, significantly enhancing the reliability of subsequent downstream applications. The inherent non-uniformity of Infrared Focal Plane Arrays (IRFPA) inevitably results in stripe noise, which severely degrades image quality and hinders downstream applications. Existing deep learning methods often struggle to strike a balance between effective denoising and the preservation of fine thermal textures. To address this issue, we propose a Bottleneck-free Channel Dual-path Aggregation Network (BCDA-Net) based on a "Perception-Reconstruction" design principle. In the perception stage, the network jointly employs the Dual-Path Channel Down-sampling (DCD) module and the Context-Guided Stripe Attention Block (CGSAB). The DCD module utilizes a channel split strategy to simultaneously extract semantic features and preserve high-frequency textures, while the CGSAB performs global context modeling on these features to precisely perceive and locate global stripe noise patterns. In the reconstruction stage, we integrate the Cascaded Dense Feature Aggregation (CDFA) module with a Bottleneck-Free Aggregation Strategy (BFAS). The CDFA utilizes the perceived information to densely aggregate features and progressively reconstruct clean image details, whereas the BFAS structurally blocks the propagation of low-resolution noise during decoding, effectively mitigating aliasing artifacts induced by deep feature upsampling. Together, these components form a complete closed loop from accurate noise perception to high-fidelity reconstruction. Extensive experiments on public and real-world datasets demonstrate that BCDA-Net maximally preserves image details while removing non-uniform stripe noise. Both objective metrics and subjective visual quality outperform existing state-of-the-art methods. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18091321 |
