Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only consider a single and fixed degradation (such as bicubic interpolation) and cannot flexibly handle complex degradations in real scenes. Therefore, designing a super-resolution (SR) model that can cope with various degradations is gradually attracting the attention of researchers. Some studies first estimate the degradation kernels and then perform degradation-adaptive SR but face the problems of estimation error amplification and insufficient high-frequency details in the results. Although blind SR algorithms based on generative adversarial networks (GAN) have greatly improved visual quality, they still suffer from pseudo-texture, mode collapse, and poor training stability. In this article, we propose a novel blind SR framework based on the stochastic normalizing flow (BlindSRSNF) to address the above problems. BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood. BlindSRSNF is easy to train and can generate photo-realistic SR results that outperform GAN-based models. Besides, we introduce a degradation representation strategy based on contrastive learning to avoid the error amplification problem caused by the explicit degradation estimation. Comprehensive experiments show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.
翻译:在真实场景中,遥感图像可能会受到多种因素的干扰,如光模糊、抽样不足和增加噪音等,从而产生复杂和多样的降解模型。目前,主流SR算法只考虑单一和固定的降解(如双立内插),无法灵活处理真实场景中的复杂降解。因此,设计一个能够应对各种降解的超级分辨率(SR)模型正在逐渐吸引研究人员的注意。一些研究首先估计降解内核,然后进行降解性反应,但面临估算错误放大和结果中不够全面频率细节的问题。虽然基于基因化对抗网络(GAN)的盲人SR算法只考虑单一和固定的降解(如双立内插),在真实场景中,它们仍然受到假文本、模式崩溃以及培训稳定性差的影响。在本篇文章中,我们提议一个基于随机正常流(BlindSRNSNF)的新盲的SR框架,以解决上述问题。 盲人SRNF学会在高分辨率图像空间的模拟中,由于低分辨率放大的图像,可以明显地显示以高分辨率为代表。