Abstract
Image colorization is a key research direction in the field of computer vision, which aims to predict the color information of grayscale images and convert them into color images. Traditional image colorization methods need to provide a large number of color points to mark each object in the image. As a result of the rapid development of convolutional neural networks, image colorization methods have also improved, with deep learning methods benefiting the most. However, due to the lack of feature quality, there are still many challenges in practical applications, such as boundary blurring. In this paper, we propose a gray image colorization method based on the Convolutional Block Attention Module (CBAM) and Pix2Pix network. Specifically, we add the CBAM module to the U-net generator network, which helps adaptively capture sensitive features, thereby enhancing the quality of features and image coloring. The effectiveness of the proposed model is verified by experiments.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call