Unsupervised Video Satellite Super-Resolution by Using Only a Single Video

Recent studies have shown that deep-learning (DL)-based methods lead to improved performance in video satellite super-resolution (SR). However, the vast majority of prior work is supervised, which is restricted to artificially generated training data (e.g., predetermined bicubic downsampling). Unfortunately, in the real world, the low-resolution (LR) satellite video frames rarely obey these restrictions. To solve this problem, we resort to unsupervised learning and propose a video satellite SR method by using only a single video. The single video SR (SingleVSR) method takes advantage of the power of DL without relying on prior high-resolution (HR) and LR pairs. In the training phase, the LR frames are alternately processed by both downsampling network (i.e., Net(LR)) and upsampling network (i.e., Net(HR)). The losses obtained by LR frames and network outputs are used to optimize both Net(LR) and Net(HR). In the testing phase, the trained Net(HR) is applied to generate the SR results of LR frames. In contrast to the existing video satellite SR methods, our SingleVSR does not require any assumption on degradation or any additional training data except for the single video to be tested. Experiments performed on Jilin-1 and OVS-1 satellite videos demonstrate the superiority of the proposed method.

Automated summary

Recent studies have shown that unsupervised deep learning methods can improve the performance of video satellite super-resolution. This research proposes a single video-based approach that does not rely on any prior high-resolution or low-resolution pairs, making it highly practical.