Saved in:
Bibliographic Details
Main Authors: Liu, Zhu, Wang, Zijun, Liu, Jinyuan, Meng, Fanqi, Ma, Long, Liu, Risheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913714682200064
author Liu, Zhu
Wang, Zijun
Liu, Jinyuan
Meng, Fanqi
Ma, Long
Liu, Risheng
author_facet Liu, Zhu
Wang, Zijun
Liu, Jinyuan
Meng, Fanqi
Ma, Long
Liu, Risheng
contents Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging
Liu, Zhu
Wang, Zijun
Liu, Jinyuan
Meng, Fanqi
Ma, Long
Liu, Risheng
Computer Vision and Pattern Recognition
Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.
title DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00905