基于无监督学习的单样本红外图像生成方法

Single-Sample Infrared Image Generation Method Based on Unsupervised Learning

针对当前可见光-红外图像数据集匮乏导致的模型特征学习能力不够以及生成图像质量低下等问题,提出了单样本的无监督学习方法来训练红外图像生成模型。首先,在数据集难以获取、匮乏的情况下,仅采用一对可见光-红外图像作为模型训练的数据,降低了数据获取的难度,解决了数据匮乏的问题。其次,为了在训练模型时充分提取图像特征,改进了网络结构。实验数据表明,本文方法能够在单样本图像生成中取得较好的效果。在艾睿光电数据集中,本文方法的峰值信噪比(Peak Signal-to-Noise Ratio, PSNR)与结构相似性(Structural Similarity, SSIM)指标分别达到了26.5588 dB和0.8846;在俄亥俄州立大学(Ohio State University, OSU)数据集上的PSNR和SSIM分别达到了30.3528 dB和0.9182。与基于风格的生成对抗网络(Style-based Generative Adversarial Network, StyleGAN)方法相比,本文方法在艾睿光电数据集上的PSNR和SSIM指标分别提高了16.07%和23.78%;在OSU数据集上的PSNR和SSIM指标分别提高了31.8%和40.4%。结果表明,本文方法在当前图像质量评价指标方面有较为明显的提高,生成的红外图像纹理细节丰富且接近于真实红外图像。该研究对于今后的红外图像生成技术优化具有一定的参考意义。

Aiming at the problems such as insufficient learning ability of model features and low quality of generated image caused by the current scarcity of visible-infrared image datasets,a single-sample unsupervised learning method to train infrared image generation model is proposed in this paper.First of all,when the dataset is difficult to obtain,only a pair of visible-infrared images are used as the data for model training,which reduces the difficulty of data acquisition and solves the problem of data scarcity.Secondly,in order to fully extract image features during the training of the model,the network structure is improved.Experimental data show that good results can be achieved in single-sample image generation by the proposed method.In the InfiRay OE dataset,peak signal-to-noise ratio(PSNR)and structural similarity(SSIM)of the proposed method reach 26.5588 dB and 0.8846,respectively.PSNR and SSIM of the Ohio State University(OSU)dataset reach 30.3528 dB and 0.9182,respectively.Compared with the style-based generative adversarial network(StyleGAN)method,PSNR and SSIM of the proposed method in the InfiRay OE dataset are increased by 16.07%and 23.78%,respectively.PSNR and SSIM of OSU dataset are increased by 31.8%and 40.4%,respectively.The results show that the image quality evaluation index of the proposed method is improved significantly,and the texture details of the generated infrared image are rich and close to the real infrared image.The research has a certain reference significance for the optimization of infrared image generation technology in the future.