Patents by Inventor Amandeep KUMAR

Amandeep KUMAR 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).

  • System and method of cross-modulated dense local fusion for few-shot image generation
    Patent number: 12100082
    Abstract: An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.
    Type: Grant
    Filed: November 9, 2022
    Date of Patent: September 24, 2024
    Assignee: Mohamed bin Zayed University of Artificial Intelligence
    Inventors: Amandeep Kumar, Ankan Kumar Bhunia, Hisham Cholakkal, Sanath Narayan, Rao Muhammad Anwer, Fahad Khan
  • SYSTEM AND METHOD OF CROSS-MODULATED DENSE LOCAL FUSION FOR FEW-SHOT IMAGE GENERATION
    Publication number: 20240161360
    Abstract: An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.
    Type: Application
    Filed: November 9, 2022
    Publication date: May 16, 2024
    Applicant: Mohamed bin Zayed University of Artificial Intelligence
    Inventors: Amandeep KUMAR, Ankan Kumar BHUNIA, Hisham CHOLAKKAL, Sanath NARAYAN, Rao Muhammad ANWER, Fahad KHAN