Unsupervised Multi-Spectral Image Super-Resolution Based on Conditional Variational Autoencoder

Unsupervised super-resolution aims to enhance the quality of images without high-resolution (HR) labels during the training stage, making it applicable to real-world scenarios. However, unsupervised super-resolution methods face the challenge of effectively learning the internal structure of images due to the absence of high-quality HR images as references. Moreover, multi-spectral remote sensing images often contain stochastic features caused by cloud and fog occlusions. These occlusions make it difficult to achieve accurate reconstruction of occluded areas through direct modeling of deep features in multi-spectral images. In this paper, we propose a method inspired by conditional variational autoencoders to address the issue of stochastic features in unsupervised multi-spectral super-resolution. Additionally, we introduce a channel attention feature fusion module to combine two types of features. We evaluated our unsupervised multi-spectral image super-resolution method using a real satellite remote sensing dataset. Experimental results demonstrate the qualitative and quantitative effectiveness of our approach.