Abstract: To enhance the environmental perception and target recognition capabilities of unmanned aerial vehicles in complex environments, the exploration of unmanned aerial vehicles mounted day-and-night single-channel natural-sensing color thermal imaging technology is undertaken. Based on deep learning technology, two image colorization techniques have been constructed: the TIVNet, an infrared image colorization network based on a multi-discriminator generative adversarial network, and the infrared image colorization network based on the semantic-guided diffusion model with regional self-segmentation RSDM. TIVNet employs a generative adversarial network architecture with multiple discriminators to directly convert infrared thermal images into colorized visible-light-like images. However, there are instances where color inaccuracies are observed in the detailed aspects of certain scenes. RSDM generates more realistic color images through a more sophisticated model, enhancing the visual impact and efficiency of information transmission in images. However, the processing speed of the current model still requires improvement. Experimental results indicate that the two proposed methods each possess distinct advantages in terms of the fidelity of image conversion and real-time processing rate. TIVNet has achieved real-time processing at a rate of not less than 40 Hz on platforms such as UAVs, demonstrating the technical feasibility. Moreover, it possesses the capability to facilitate equipment transformation applications based on specific application requirements, thereby providing a novel technological means for the application of UAVs in both military and civilian domains.