Local-Global Temporal Difference Learning for Satellite Video Super-Resolution

Optical-flow-based and kernel-based approaches have been extensively explored for temporal compensation in satellite Video Super-Resolution (VSR). However, these techniques are less generalized in large-scale or complex scenarios, especially in satellite videos. In this paper, we propose to exploit the well-defined temporal difference for efficient and effective temporal compensation. To fully utilize the local and global temporal information within frames, we systematically modeled the short-term and long-term temporal discrepancies since we observe that these discrepancies offer distinct and mutually complementary properties. Specifically, we devise a Short-term Temporal Difference Module (S-TDM) to extract local motion representations from RGB difference maps between adjacent frames, which yields more clues for accurate texture representation. To explore the global dependency in the entire frame sequence, a Long-term Temporal Difference Module (L-TDM) is proposed, where the differences between forward and backward segments are incorporated and activated to guide the modulation of the temporal feature, leading to a holistic global compensation. Moreover, we further propose a Difference Compensation Unit (DCU) to enrich the interaction between the spatial distribution of the target frame and temporal compensated results, which helps maintain spatial consistency while refining the features to avoid misalignment. Rigorous objective and subjective evaluations conducted across five mainstream video satellites demonstrate that our method performs favorably against state-of-the-art approaches. Code will be available at https://github.com/XY-boy/LGTD.

I. Introduction

Compared to traditional static remote sensing images, video satellite provides continuous information to a specific area, which is crucial for dynamic earth observation. Therefore, it has been widely applied to dynamic scene applications such as change detection [1], object tracking [2], and traffic monitoring [3]. However, the spatial resolution of satellite video is usually contaminated by the complex aerial environment, limited by the intrinsic resolution of satellite video sensors (~1m), and degraded by data compression. Consequently, high-frequency information in the satellite video may be lost, which dramatically reduces the visual quality and degrades performance in subsequent applications. To this end, it is essential to improve the spatial resolution of satellite videos.