公开(公告)号：US12100082B2

公开(公告)日：2024-09-24

申请号：US17983952

申请日：2022-11-09

申请人： Mohamed bin Zayed University of Artificial Intelligence

发明人： Amandeep Kumar ,  Ankan Kumar Bhunia ,  Hisham Cholakkal ,  Sanath Narayan ,  Rao Muhammad Anwer ,  Fahad Khan

IPC分类号： G06T11/60 ,  G06T9/00 ,  G06V10/44 ,  G06V10/74 ,  G06V10/80 ,  G06V10/82

CPC分类号： G06T11/60 ,  G06T9/00 ,  G06V10/44 ,  G06V10/761 ,  G06V10/806 ,  G06V10/82 ,  G06T2200/24

摘要： 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.