Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution
This work addresses a domain-specific problem for UAV-based applications like security and agriculture, offering an incremental improvement through a novel guidance disentanglement approach.
The paper tackles the problem of generating effective guidance features for optics-guided thermal UAV image super-resolution under varying conditions by proposing a Guidance Disentanglement network (GDNet) that disentangles optical image representations based on UAV scenario attributes. It achieves significant performance improvements over state-of-the-art methods, particularly in low-light and foggy environments, and introduces a new large-scale dataset (VGTSR2.0) with 3,500 image pairs.
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.