Patents by Inventor Seoungyoon KANG

Seoungyoon KANG 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).

  • Patent number: 11915513
    Abstract: Provided are an apparatus for performing leveling of a person image and an operating method thereof. The method includes: receiving an original person image; selecting an arbitrary latent vector in a latent space; generating a virtual person image based on the latent vector; optimizing the latent vector such that identity similarity between the original person image and the virtual person image increases; manipulating the optimized latent vector; and generating a levelled person image corresponding to the original person image, by using the manipulated latent vector.
    Type: Grant
    Filed: April 22, 2022
    Date of Patent: February 27, 2024
    Assignees: NCSOFT CORPORATION, INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY
    Inventors: Seoungyoon Kang, Min Jae Kim, Moo Kyung Song, Hyunjung Shim, Gun Hee Lee
  • Publication number: 20220375254
    Abstract: Provided are an apparatus for performing leveling of a person image and an operating method thereof. The method includes: receiving an original person image; selecting an arbitrary latent vector in a latent space; generating a virtual person image based on the latent vector; optimizing the latent vector such that identity similarity between the original person image and the virtual person image increases; manipulating the optimized latent vector; and generating a levelled person image corresponding to the original person image, by using the manipulated latent vector.
    Type: Application
    Filed: April 22, 2022
    Publication date: November 24, 2022
    Applicants: NCSOFT CORPORATION, INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY
    Inventors: Seoungyoon KANG, Min Jae KIM, Moo Kyung SONG, Hyunjung SHIM, Gun Hee LEE