Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution

TL;DR

This paper introduces GDNet, a novel guidance disentanglement network that enhances thermal UAV image super-resolution by disentangling optical guidance features for robustness across diverse conditions, supported by a new large-scale dataset.

Contribution

The paper proposes a guidance disentanglement network with an attribute-aware fusion module and introduces VGTSR2.0, a large-scale benchmark dataset for UAV thermal image super-resolution.

Findings

GDNet outperforms state-of-the-art methods in diverse conditions

Significant improvements in low-light and foggy environments

VGTSR2.0 facilitates research in complex UAV scenarios

Abstract

Optics-guided Thermal UAV image Super-Resolution (OTUAV-SR) has attracted significant research interest due to its potential applications in security inspection, agricultural measurement, and object detection. Existing methods often employ single guidance model to generate the guidance features from optical images to assist thermal UAV images super-resolution. However, single guidance models make it difficult to generate effective guidance features under favorable and adverse conditions in UAV scenarios, thus limiting the performance of OTUAV-SR. To address this issue, we propose a novel Guidance Disentanglement network (GDNet), which disentangles the optical image representation according to typical UAV scenario attributes to form guidance features under both favorable and adverse conditions, for robust OTUAV-SR. Moreover, we design an attribute-aware fusion module to combine all attribute-based optical guidance features, which could form a more discriminative representation and fit the attribute-agnostic guidance process. To facilitate OTUAV-SR research in complex UAV scenarios, we introduce VGTSR2.0, a large-scale benchmark dataset containing 3,500 aligned optical-thermal image pairs captured under diverse conditions and scenes. Extensive experiments on VGTSR2.0 demonstrate that GDNet significantly improves OTUAV-SR performance over state-of-the-art methods, especially in the challenging low-light and foggy environments commonly encountered in UAV scenarios. The dataset and code will be publicly available at https://github.com/Jocelyney/GDNet.