Self-Supervised Infrared Image Denoising via Adaptive Gradient-Perception Network for FPN Suppression
Open Access
- 5 November 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (21) , 4334
Abstract
Current denoising algorithms in infrared imaging systems predominantly target either high-frequency stripe noise or Gaussian noise independently, failing to adequately address the prevalent hybrid noise in real-world scenarios. To tackle this challenge, we propose a convolutional neural network (CNN)-based approach with a refined composite loss function, specifically designed for hybrid noise removal in raw infrared images. Our method employs a residual network backbone integrated with an adaptive weighting mechanism and edge-preserving loss, enabling joint modeling of multiple noise types while safeguarding structural edges. Unlike reference-based CNN denoising methods requiring clean images, our solution leverages intrinsic gradient variations within image sequences for adaptive smoothing, eliminating dependency on ground-truth data during training. Rigorous experiments conducted on three public datasets have demonstrated the optimal or suboptimal performance of our method in mixed noise suppression and detail preservation (PSNR > 32.13/SSIM > 0.8363).Keywords
This publication has 32 references indexed in Scilit:
- IDTransformer: Infrared image denoising method based on convolutional transposed self-attentionAlexandria Engineering Journal, 2024
- DSEUNet: A lightweight UNet for dynamic space grouping enhancement for skin lesion segmentationExpert Systems with Applications, 2024
- Low-Light Image Enhancement via Regularized Gaussian Fields ModelNeural Processing Letters, 2023
- Eres-UNet++: Liver CT image segmentation based on high-efficiency channel attention and Res-UNet++Computers in Biology and Medicine, 2023
- Infrared image denoising via adversarial learning with multi-level feature attention networkInfrared Physics & Technology, 2022
- Flexible infrared images destriping algorithm with L1-based sparse regularization for wide-field astronomical imagesInfrared Physics & Technology, 2022
- Spatial-noise subdivision evaluation model of uncooled infrared detectorInfrared Physics & Technology, 2021
- Infrared thermal imaging denoising method based on second-order channel attention mechanismInfrared Physics & Technology, 2021
- Remote sensing images destriping using unidirectional hybrid total variation and nonconvex low-rank regularizationJournal of Computational and Applied Mathematics, 2020
- Robust destriping method based on data-driven learningInfrared Physics & Technology, 2018