Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
This work addresses the challenge of IR image super-resolution for applications like surveillance and remote sensing, representing an incremental improvement over existing deep learning methods.
The paper tackles the problem of low-resolution infrared (IR) image super-resolution by proposing HetSRWGAN, a lightweight GAN framework using heterogeneous convolution and adversarial training, which achieves consistently better performance in qualitative and quantitative evaluations with more stable training.
Image super-resolution is important in many fields, such as surveillance and remote sensing. However, infrared (IR) images normally have low resolution since the optical equipment is relatively expensive. Recently, deep learning methods have dominated image super-resolution and achieved remarkable performance on visible images; however, IR images have received less attention. IR images have fewer patterns, and hence, it is difficult for deep neural networks (DNNs) to learn diverse features from IR images. In this paper, we present a framework that employs heterogeneous convolution and adversarial training, namely, heterogeneous kernel-based super-resolution Wasserstein GAN (HetSRWGAN), for IR image super-resolution. The HetSRWGAN algorithm is a lightweight GAN architecture that applies a plug-and-play heterogeneous kernel-based residual block. Moreover, a novel loss function that employs image gradients is adopted, which can be applied to an arbitrary model. The proposed HetSRWGAN achieves consistently better performance in both qualitative and quantitative evaluations. According to the experimental results, the whole training process is more stable.