The field of UAV-based perception is rapidly advancing, with a focus on developing robust and accurate methods for multimodal image registration and fusion. Recent research has highlighted the importance of addressing the challenges posed by diverse environmental conditions, such as varying lighting, weather, and camera angles. To this end, innovative approaches have been proposed, including the use of hyperbolic space for image alignment and the development of specialized benchmark datasets. These advancements have the potential to significantly improve the performance of UAV-based perception systems, enabling more effective detection, tracking, and identification of objects in complex scenarios. Noteworthy papers include: ATR-UMMIM, which introduces a comprehensive benchmark dataset for multimodal image registration in UAV-based applications, and Hyperbolic Cycle Alignment, which proposes a novel image registration method based on hyperbolic space. CST Anti-UAV is also notable for its thermal infrared benchmark for tiny UAV tracking in complex scenes.