摘要
红外图像在计算机视觉领域应用广泛。受制于采集条件,高质量红外图像数据集规模较小。把可见光图像转换为红外图像,是扩充红外数据集的有效手段。现有生成方法多依赖有监督学习,需要大量配对数据。为此,提出基于双重语义对比学习的无监督红外图像生成方法DSCGAN。该方法采用双向转换架构,通过语义对比学习增强图像内容保持能力和红外特征学习能力。损失函数增加几何一致性损失,协助保留可见光图像的原始结构与细节。同时,构建多尺度PatchGAN判别器,增强判别能力,提升生成图片的真实感。在AVIID-1,AVIID-2和Day-DroneVehicle数据集上的实验表明,DSCGAN在多项指标上优于对比方法,生成的红外图像热辐射分布更合理,视觉质量更优。在AVIID-1数据集中,DSCGAN的SSIM值提升至0.8144,FID分数降低至0.1456。在Day-DroneVehicle数据集中,DSCGAN的PSNR值提升至18.14,LPIPS值降低至0.2949。所提方法为无监督红外图像生成提供了新思路,可进一步应用于红外目标检测和场景分割等下游任务。
Infrared images are widely used in computer vision,but high-quality infrared image datasets are limited in scale due to restricted acquisition conditions.To address this problem,converting visible datasets to infrared datasets has become an effective way.Existing generation methods generally rely on supervised learning,which requires a large amount of paired data that is extremely difficult to obtain in practical applications.This paper proposes an unsupervised infrared image generation method named DSCGAN.This method adopts a bidirectional transformation architecture and introduces semantic contrast learning to enhance the ability to preserve image content and learn discriminative infrared features.The geometric consistency loss is introduced to preserve the original structure and details of visible images effectively.Meanwhile,a multi-scale PatchGAN discriminator is constructed to improve discriminative capability and enhance the realism of generated images.Experimental results on the AVIID-1,AVIID-2,and Day-DroneVehicle datasets show that DSCGAN outperforms the comparison methods in several metrics,and the generated infrared images exhibit a more reasonable thermal radiation distribution and better visual quality.In the AVIID-1 dataset,the SSIM value increases to 0.8144,and the FID score decreases to 0.1456.In the Day-DroneVehicle dataset,the PSNR value improves to 18.14,while the LPIPS value drops to 0.2949.This study provides a new idea for unsupervised infrared image gene-ration,with potential applications in infrared target detection,infrared scene segmentation,and other downstream tasks.
作者
程梓萌
杨馨悦
艾浩军
王中元
CHENG Zimeng;YANG Xinyue;AI Haojun;WANG Zhongyuan(School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,China;Key Laboratory of Aerospace Information Security and Trusted Computing,Ministry of Education,Wuhan University,Wuhan 430072,China;School of Computer Science,Wuhan University,Wuhan 430079,China)
出处
《计算机科学》
2026年第4期260-268,共9页
Computer Science
基金
湖北省国际科技合作项目(2025EHA043)。
关键词
图像到图像转换
语义对比学习
红外图像生成
多尺度判别器
几何一致性约束
Image-to-image translation
Semantic contrastive learning
Infrared image generation
Multi-scale discriminator
Geometric consistency constraint
