公开(公告)号：US20240303494A1

公开(公告)日：2024-09-12

申请号：US18666613

申请日：2024-05-16

Applicant: NVIDIA Corporation

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

IPC: G06N3/088 ,  G06F18/214 ,  G06F18/2431 ,  G06T3/02 ,  G06T3/60 ,  G06T7/73 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06N3/088 ,  G06F18/214 ,  G06F18/2431 ,  G06T3/02 ,  G06T3/60 ,  G06T7/74 ,  G06V10/764 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084

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.

公开(公告)号：US20240161250A1

公开(公告)日：2024-05-16

申请号：US18485239

申请日：2023-10-11

Applicant: NVIDIA CORPORATION

Inventor： Yogesh BALAJI ,  Timo Oskari AILA ,  Miika AITTALA ,  Bryan CATANZARO ,  Xun HUANG ,  Tero Tapani KARRAS ,  Karsten KREIS ,  Samuli LAINE ,  Ming-Yu LIU ,  Seungjun NAH ,  Jiaming SONG ,  Arash VAHDAT ,  Qinsheng ZHANG

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Techniques are disclosed herein for generating a content item. The techniques include performing one or more first denoising operations based on an input and a first machine learning model to generate a first content item, and performing one or more second denoising operations based on the input, the first content item, and a second machine learning model to generate a second content item, where the first machine learning model is trained to denoise content items having an amount of corruption within a first corruption range, the second machine learning model is trained to denoise content items having an amount of corruption within a second corruption range, and the second corruption range is lower than the first corruption range.