Patents by Inventor Moon Su CHA

Moon Su CHA has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Method for learning cross-domain relations based on generative adversarial networks
    Patent number: 10713294
    Abstract: A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. A provided architecture includes two coupled GANs: a first GAN learning a translation of images from domain A to domain B, and a second GAN learning a translation of images from domain B to domain A. A loop formed by the first GAN and the second GAN causes sample images to be reconstructed into an original domain after being translated into a target domain. Therefore, loss functions representing reconstruction losses of the images may be used to train generative models.
    Type: Grant
    Filed: March 7, 2019
    Date of Patent: July 14, 2020
    Assignee: SK TELECOM CO., LTD.
    Inventors: Taek Soo Kim, Moon Su Cha, Ji Won Kim
  • METHOD FOR LEARNING CROSS-DOMAIN RELATIONS BASED ON GENERATIVE ADVERSARIAL NETWORKS
    Publication number: 20190205334
    Abstract: A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. A provided architecture includes two coupled GANs: a first GAN learning a translation of images from domain A to domain B, and a second GAN learning a translation of images from domain B to domain A. A loop formed by the first GAN and the second GAN causes sample images to be reconstructed into an original domain after being translated into a target domain. Therefore, loss functions representing reconstruction losses of the images may be used to train generative models.
    Type: Application
    Filed: March 7, 2019
    Publication date: July 4, 2019
    Inventors: Taek Soo KIM, Moon Su CHA, Ji Won KIM
  • Method for learning cross-domain relations based on generative adversarial networks
    Patent number: 10275473
    Abstract: A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. A provided architecture includes two coupled GANs: a first GAN learning a translation of images from domain A to domain B, and a second GAN learning a translation of images from domain B to domain A. A loop formed by the first GAN and the second GAN causes sample images to be reconstructed into an original domain after being translated into a target domain. Therefore, loss functions representing reconstruction losses of the images may be used to train generative models.
    Type: Grant
    Filed: August 9, 2017
    Date of Patent: April 30, 2019
    Assignee: SK TELECOM CO., LTD.
    Inventors: Taek Soo Kim, Moon Su Cha, Ji Won Kim
  • METHOD FOR LEARNING CROSS-DOMAIN RELATIONS BASED ON GENERATIVE ADVERSARIAL NETWORKS
    Publication number: 20180314716
    Abstract: A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. A provided architecture includes two coupled GANs: a first GAN learning a translation of images from domain A to domain B, and a second GAN learning a translation of images from domain B to domain A. A loop formed by the first GAN and the second GAN causes sample images to be reconstructed into an original domain after being translated into a target domain. Therefore, loss functions representing reconstruction losses of the images may be used to train generative models.
    Type: Application
    Filed: August 9, 2017
    Publication date: November 1, 2018
    Inventors: Taek Soo KIM, Moon Su CHA, Ji Won KIM