Image Colorization
Image colorization aims to automatically add realistic color to grayscale images or videos, a challenging problem due to inherent ambiguity. Current research focuses on improving color accuracy and consistency, often employing generative adversarial networks (GANs), transformers, and diffusion models, sometimes incorporating additional modalities like text descriptions or audio to guide the process. These advancements have implications for various fields, including digital image restoration, historical preservation, and enhancing the capabilities of other imaging technologies like LiDAR. The ongoing emphasis is on achieving greater controllability, realism, and efficiency in colorization algorithms.
Papers
December 7, 2023
October 23, 2023
September 25, 2023
August 7, 2023
August 3, 2023
May 24, 2023
May 23, 2023
April 24, 2023
April 21, 2023
February 12, 2023
December 22, 2022
December 21, 2022
December 5, 2022
November 7, 2022
October 25, 2022
October 20, 2022
September 22, 2022
September 13, 2022