Colorization of infrared images based on feature fusion and contrastive learning

Converting infrared images to RGB images that match human eye perception is a challenging task. Current in-frared image coloring techniques can bring visual improvements, but still suffer from texture distortion, blurred details, and poor image quality. In this paper, we work on solving the above problems. First, we design an im-proved generator structure. On the basis of Unet, we add dense convolutional blocks and skip connections to integrate low-level detail information with high-level semantic information. The developed generator can cap-ture features at different levels and integrate them by feature fusion. It ensures that the captured features are not lost. Second, we design a new contrastive loss function. Based on the contrastive learning framework, this function focuses on learning common features between similar instances and distinguishing differences between non-similar instances. This ensures the consistency of the content and structure of the images. Finally, an in-depth contrast analysis is conducted based on commonly used datasets to demonstrate the superior colorization performance of our method against the state-of-the-art approaches.

Automated summary

This paper proposes an improved generator structure and a new contrastive loss function to tackle the problem of converting infrared images to RGB images that match human eye perception. The developed generator effectively captures features at different levels and integrates them by feature fusion. The new contrastive loss function ensures the consistency of the content and structure of the images. Experimental results demonstrate the superior colorization performance of our method compared to state-of-the-art approaches.