Patents by Inventor Kevin Jonathan Shih

Kevin Jonathan Shih 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).

  • SYNTHESIZING VIDEO FROM AUDIO USING ONE OR MORE NEURAL NETWORKS
    Publication number: 20230035306
    Abstract: Apparatuses, systems, and techniques are presented to generate media content.
    Type: Application
    Filed: July 21, 2021
    Publication date: February 2, 2023
    Inventors: Ming-Yu Liu, Koki Nagano, Yeongho Seol, Jose Rafael Valle Gomes da Costa, Jaewoo Seo, Ting-Chun Wang, Arun Mallya, Sameh Khamis, Wei Ping, Rohan Badlani, Kevin Jonathan Shih, Bryan Catanzaro, Simon Yuen, Jan Kautz
  • UPSAMPLING AN IMAGE USING ONE OR MORE NEURAL NETWORKS
    Publication number: 20220222778
    Abstract: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.
    Type: Application
    Filed: March 31, 2022
    Publication date: July 14, 2022
    Inventors: Shiqiu Liu, Robert Thomas Pottorff, Guilin Liu, Karan Sapra, Jon Barker, David Tarjan, Pekka Janis, Edvard Olav Valter Fagerholm, Lei Yang, Kevin Jonathan Shih, Marco Salvi, Timo Roman, Andrew Tao, Bryan Christopher Catanzaro
  • DISENTANGLEMENT OF IMAGE ATTRIBUTES USING A NEURAL NETWORK
    Publication number: 20220180528
    Abstract: Apparatuses, systems, and techniques to perform unsupervised keypoint or landmark learning using one or more neural networks. In at least one embodiment, one or more neural networks use pose and appearance information to construct a foreground and a background, which are then used to reconstruct an input image and determine loss values to train the one or more neural networks.
    Type: Application
    Filed: February 23, 2022
    Publication date: June 9, 2022
    Inventors: Aysegul Dundar, Kevin Jonathan Shih, Animesh Garg, Robert Thomas Pottorff, Andrew Tao, Bryan Christopher Catanzaro
  • UPSAMPLING AN IMAGE USING ONE OR MORE NEURAL NETWORKS
    Publication number: 20220114702
    Abstract: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights.
    Type: Application
    Filed: August 19, 2021
    Publication date: April 14, 2022
    Inventors: Shiqiu Liu, Robert Pottorff, Guilin Liu, Karan Sapra, Jon Barker, David Tarjan, Pekka Janis, Edvard Fagerholm, Lei Yang, Kevin Jonathan Shih, Marco Salvi, Timo Roman, Andrew Tao, Bryan Catanzaro