公开(公告)号：WO2021211750A1

公开(公告)日：2021-10-21

申请号：PCT/US2021/027343

申请日：2021-04-14

Applicant: NVIDIA CORPORATION

Inventor： LIU, Ming-Yu ,  WANG, Ting-Chun ,  MALLYA, Arun Mohanray ,  KARRAS, Tero Tapani ,  LAINE, Samuli Matias ,  LUEBKE, David Patrick ,  LEHTINEN, Jaakko ,  AITTALA, Miika Samuli ,  AILA, Timo Oskari

IPC: H04N19/00 ,  G06F3/14 ,  H04N19/20 ,  H04N21/234 ,  H04N21/63 ,  H04N19/46 ,  G06N3/02

Abstract: Apparatuses, systems, and techniques to perform compression of video data using neural networks to facilitate video streaming, such as video conferencing. In at least one embodiment, a sender transmits to a receiver a key frame from video data and one or more keypoints identified by a neural network from said video data, and a receiver reconstructs video data using said key frame and one or more received keypoints.

公开(公告)号：WO2020159890A1

公开(公告)日：2020-08-06

申请号：PCT/US2020/015262

申请日：2020-01-27

Applicant: NVIDIA CORPORATION

Inventor： LIU, Ming-Yu ,  HUANG, Xun ,  KARRAS, Tero ,  AILA, Timo ,  LEHTINEN, Jaakko

IPC: G06K9/62 ,  G06N3/08 ,  G06T11/00

Abstract: A few-shot, unsupervised image-to-image translation ("FUNIT") algorithm is disclosed that accepts as input images of previously-unseen target classes. These target classes are specified at inference time by only a few images, such as a single image or a pair of images, of an object of the target type. A FUNIT network can be trained using a data set containing images of many different object classes, in order to translate images from one class to another class by leveraging few input images of the target class. By learning to extract appearance patterns from the few input images for the translation task, the network learns a generalizable appearance pattern extractor that can be applied to images of unseen classes at translation time for a few-shot image-to-image translation task.