PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 29, 2026Remote Sensing0 citationsOpen Access

BCDA-Net: A Bottleneck-Free Channel Dual-Path Aggregation Network for Infrared Image Destriping

View Full Paper
LCLingzhi ChenFDFeng DongLHLingfeng Huang

Key Points

  • This research aims to enhance image quality by addressing stripe noise in infrared images using a novel network architecture.
  • Developed BCDA-Net based on Perception-Reconstruction design principle.
  • Implemented Dual-Path Channel Down-sampling and Context-Guided Stripe Attention Block for feature extraction.
  • Integrated Cascaded Dense Feature Aggregation with Bottleneck-Free Aggregation Strategy for reconstruction.
  • Successfully preserved image details while removing stripe noise.
  • Outperformed existing state-of-the-art methods in both objective metrics and visual quality.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Chen et al. (2026) studied this question.

synapsesocial.com/papers/69f154a4879cb923c4944d32https://doi.org/10.3390/rs18091321
Ask AI
Helpful
Bookmark
Share
View Full Paper