Remote sensing often faces challenges such as motion blur, overexposure, and limited dynamic range, particularly in extreme lighting and high-speed scenarios. To overcome these limitations, this study introduces a novel framework that integrates event cameras, infrared imaging, and deep learning techniques for robust and high-quality image fusion.

Event cameras capture rapid light intensity changes with high dynamic range and microsecond-level temporal resolution, making them ideal for preserving motion details and texture in challenging environments. Infrared imaging complements this by providing thermal data unaffected by lighting variations. By combining these two modalities, the framework leverages their complementary strengths for improved scene understanding.

The proposed framework employs deep learning to perform three key tasks: reconstructing visible textures from event data, deblurring infrared images guided by event-based motion cues, and fusing the features of both modalities. A bi-level optimization process reduces redundancy while preserving essential information, resulting in clearer and more detailed fused images.

Experiments on synthetic and real-world datasets demonstrate the framework's ability to outperform state-of-the-art methods, particularly in dynamic and low-visibility conditions. This work highlights the transformative potential of integrating event cameras and infrared imaging with deep learning, offering a powerful solution for complex remote sensing scenarios.