Aug 19, 2021 · In this work, we propose GCP-Colorization that leverages the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN) ...

Official code for ICCV 2021 paper "Towards Vivid and Diverse Image Colorization with Generative Color Prior".

Thanks to the powerful generative color prior and delicate designs, our method could pro- duce vivid colors with a single forward pass. Moreover, it is highly ...

In this work, we aim at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks ( ...

This work aims at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN) ...

(1) We develop a unified framework to leverage rich and diverse generative color prior for automatic colorization. (2) Our method allows us to obtain diverse ...

Request PDF | On Oct 1, 2021, Yanze Wu and others published Towards Vivid and Diverse Image Colorization with Generative Color Prior | Find, read and cite ...

As GAN inversions also incorporate pretrained GANs as a prior to guide the colorization process, we further compare the results of our method against results of ...

README.md · Issues 5 · Pull requests 1

Jul 20, 2022 · In this paper, we propose BigColor, a novel colorization approach that provides vivid colorization for diverse in-the-wild images with complex structures.