公开(公告)号：US11948349B2

公开(公告)日：2024-04-02

申请号：US17400150

申请日：2021-08-12

Applicant: FUJIFILM Corporation

Inventor： Akira Kudo ,  Yoshiro Kitamura

IPC: G06K9/62 ,  G06F18/21 ,  G06F18/214 ,  G06K9/68 ,  G06V10/10 ,  G06V10/12 ,  G06V10/82 ,  G06V30/24 ,  A61B6/03

CPC classification number: G06V10/82 ,  G06F18/2148 ,  G06F18/2185 ,  G06V10/12 ,  G06V10/16 ,  G06V30/2504 ,  A61B6/032 ,  G06V2201/03

Abstract: Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.

公开(公告)号：US12217387B2

公开(公告)日：2025-02-04

申请号：US17400142

申请日：2021-08-12

Applicant: FUJIFILM Corporation

Inventor： Akira Kudo ,  Yoshiro Kitamura

IPC: G06T3/4053 ,  G06N3/045 ,  G06N3/088 ,  G06T3/40 ,  G06T3/4046 ,  G06T5/20 ,  G06T5/70

Abstract: Provided are a learning method and a learning system of a generative model, a program, a learned model, and a super resolution image generating device that can handle input data of any size and can suppress the amount of calculation at the time of image generation. A learning method according to an embodiment of the present disclosure is a learning method for performing machine learning of a generative model that estimates, from a first image, a second image including higher resolution image information than the first image, the method comprising using a generative adversarial network including a generator which is the generative model and a discriminator which is an identification model that identifies whether provided data is data of a correct image for learning or data derived from an output from the generator and implementing a self-attention mechanism only in a network of the discriminator among the generator and the discriminator.

公开(公告)号：US12254553B2

公开(公告)日：2025-03-18

申请号：US17692172

申请日：2022-03-11

Applicant: FUJIFILM Corporation

Inventor： Akira Kudo ,  Yoshiro Kitamura

IPC: G06T15/00 ,  G06T3/4046

Abstract: An image generation device derives, for a subject including a specific structure, a subject model representing the subject by deriving each feature amount of the target image having the at least one representation format and combining the feature amounts based on the target image. A latent variable derivation unit derives a latent variable obtained by dimensionally compressing a feature of the subject model according to the target information based on the target information and the subject model. A virtual image derivation unit outputs a virtual image having the representation format represented by the target information based on the target information, the subject model, and the latent variable.

公开(公告)号：US20230306605A1

公开(公告)日：2023-09-28

申请号：US18170532

申请日：2023-02-17

Applicant: FUJIFILM Corporation

Inventor： Saeko SASUGA ,  Yoshiro Kitamura ,  Akira Kudo

IPC: G06T7/11 ,  G06T11/00 ,  G06T7/174 ,  G06T7/00 ,  G16H30/40

CPC classification number: G06T7/11 ,  G06T11/00 ,  G06T7/174 ,  G06T7/0012 ,  G16H30/40 ,  G06T2207/30008 ,  G06T2207/30096 ,  G06T2207/20081

Abstract: A processor is configured to acquire an original image and a mask image in which masks are applied to one or more regions respectively representing one or more objects including a target object in the original image, derive a pseudo mask image by processing the mask in the mask image, and derive a pseudo image that has a region based on a mask included in the pseudo mask image and has the same representation format as the original image, based on the original image and the pseudo mask image.