An Adaptive Super-Resolution Network for Drone Ship Images

TL;DR

This paper introduces a new super-resolution network for improving the quality of drone-captured ship images to enhance vessel identification.

Contribution

The novel adaptive super-resolution framework includes a static feature extraction stage and a dynamic scene reconstruction stage tailored for drone ship images.

Findings

The proposed framework outperforms existing state-of-the-art algorithms in restoring drone-captured ship images.

A high-resolution dataset of drone ship images was constructed to improve model generalizability and effectiveness.

Abstract

Uncovering latent structures from complex, degraded data is a central challenge in modern unsupervised learning, with critical implications for downstream tasks. This principle is exemplified in the domain of aerial imagery, where the quality of images captured by drones is often compromised by complex, flight-induced degradations, thereby raising the information entropy and obscuring essential semantic patterns. Conventional super-resolution methods, trained on generic data, fail to restore these unique artifacts, thereby limiting their effectiveness for vessel identification, a task that fundamentally relies on clear pattern recognition. To bridge this gap, we introduce a novel adaptive super-resolution framework for ship images captured by drones. The approach integrates a static stage for foundational feature extraction and a dynamic stage for adaptive scene reconstruction, enabling robust performance in complex aerial environments. Furthermore, to ensure the super-resolution model’s generalizability and effectiveness, we optimize the design of degradation methods based on the characteristics of drone aerial images and construct a high-resolution dataset of ship images captured by drones. Extensive experiments demonstrate that our method surpasses existing state-of-the-art algorithms, confirming the efficacy of our proposed model and dataset.

Figures