公开(公告)号：US20250166142A1

公开(公告)日：2025-05-22

申请号：US18842100

申请日：2023-03-02

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Michael DANNER ,  Lev MARKHASIN ,  Hans WOLFF

IPC: G06T5/77 ,  G06T5/60 ,  G06T11/60

Abstract: An image processing device is disclosed, featuring interface circuitry to receive image data representing a first image with an aspect ratio smaller than one. This image could be a photograph or a still frame from a video. The device's processing circuitry generates a second image with an aspect ratio greater than one by adding image areas to the lateral sides of the first image. The processing circuitry extends the background into these added areas and identifies foreground objects. If a foreground object is incomplete, the device determines and adds a visual representation of the missing part to complete the object in the extended image areas.

公开(公告)号：US20240193891A1

公开(公告)日：2024-06-13

申请号：US18521009

申请日：2023-11-28

Applicant: Sony Semiconductor Solutions Corporation ,  Technische Universität München

Inventor： Lev MARKHASIN ,  Iheb BELGACEM ,  Shivangi ANEJA ,  Matthias NIEßNER ,  Angela DAI

IPC: G06T19/20 ,  G06T15/04 ,  G06T17/20

CPC classification number: G06T19/20 ,  G06T15/04 ,  G06T17/20

Abstract: A method for user command-guided editing of an initial textured 3D morphable model of an object comprising: obtaining the initial textured 3D morphable model of the object comprising an initial texture map and an initial 3D mesh model of the object; and determining an edited texture map of the object corresponding to the user command by editing the initial texture map of the object based on a first artificial neural network; and/or determining an edited 3D mesh model of the object corresponding to the user command by editing the initial 3D mesh model of the object based on a second artificial neural network; and generating an edited textured 3D morphable model of the object corresponding to the user command based on the edited texture map of the object and/or the edited 3D mesh model of the object.

公开(公告)号：US20230276146A1

公开(公告)日：2023-08-31

申请号：US18015961

申请日：2021-07-19

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Lev MARKHASIN ,  Stephen TIEDEMANN ,  Stefan UHLICH ,  Bi WANG

IPC: H04N25/77

CPC classification number: H04N25/77

Abstract: An image processing circuitry configured to: store, based on an obtained command, a first image identifier of first image data or the first image data on a write-once-read-many memory, wherein the first image identifier is generated based on the first image data such that it is unique for the first image data.

公开(公告)号：US20230252808A1

公开(公告)日：2023-08-10

申请号：US18015088

申请日：2021-07-08

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Lev MARKHASIN ,  Stephen TIEDEMANN ,  Stefan UHLICH ,  Bi WANG

IPC: G06V20/70 ,  G06V10/764 ,  G06T1/00 ,  H04L9/00

CPC classification number: G06V20/70 ,  G06T1/0021 ,  G06V10/764 ,  H04L9/50 ,  G06T2201/005

Abstract: Abstract: An image processing circuitry configured to: generate, based on obtained image data, a visual content word sequence indicative for a visual content of an image represented by the obtained image data; and generate, based on the generated visual content word sequence, an image signature for the image.

公开(公告)号：US20220027732A1

公开(公告)日：2022-01-27

申请号：US17376195

申请日：2021-07-15

Applicant: Sony Semiconductor Solutions Corporation ,  Politechnico di Torino

Inventor： Ali ARSLAN ,  Matteo TESTA ,  Lev MARKHASIN ,  Tiziano BIANCHI ,  Enrico MAGLI

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: The present disclosure relates to an apparatus for image recognition. The apparatus comprises a machine learning network configured to map first and second input image data to either a first or a second predefined target probability distribution, depending on whether the first and second input image data correspond to matching or non-matching images, wherein an output of the machine learning network matching the first target probability distribution is indicative of matching images and an output of the machine learning network matching the second target probability distribution is indicative of non-matching images. The present disclosure also relates to a method for training the apparatus for image recognition.

公开(公告)号：US20210374221A1

公开(公告)日：2021-12-02

申请号：US17327770

申请日：2021-05-24

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Lev MARKHASIN ,  Bi WANG

IPC: G06F21/32 ,  G06F3/01 ,  G06K9/00 ,  G06N3/08

Abstract: The present disclosure relates to a method for authenticating a user. The method comprises recording image data of the user and deriving at least one first facial feature of the user's face and at least one first gesture feature of one or more gestures of the user from the image data. The method further provides for determining a degree of access of the user to data depending on whether the first gesture feature corresponds to at least one predetermined second gesture feature and whether the first facial feature corresponds to at least one predetermined second facial feature.

公开(公告)号：US20230195906A1

公开(公告)日：2023-06-22

申请号：US18077305

申请日：2022-12-08

Applicant: Sony Semiconductor Solutions Corporation ,  Technische Universität München - TUM

Inventor： Shivangi ANEJA ,  Lev MARKHASIN ,  Matthias NIEßNER ,  Stefan UHLICH ,  Bi WANG

IPC: G06F21/60 ,  H04L9/00 ,  H04L9/32

CPC classification number: G06F21/602 ,  H04L9/50 ,  H04L9/3239

Abstract: An information processing device, wherein the information processing device includes circuitry configured to:

copy, in response to an instruction for play back of a content, encrypted content data;
decrypt the copied encrypted content data for obtaining the content data representing the content; and
apply a data protection algorithm on the content data to generate protected content data representing protected content, wherein the protected content is played back.

公开(公告)号：US20210264322A1

公开(公告)日：2021-08-26

申请号：US17179451

申请日：2021-02-19

Applicant: Sony Semiconductor Solutions Corporation

Inventor： Lev MARKHASIN ,  Shangyin GAO

IPC: G06N20/20 ,  G06K9/62

Abstract: Examples relate to a computer-implemented system, a computer-implemented method and a computer program for adapting a machine-learning-architecture, and to a computer-implemented system, a computer-implemented method and a computer program and for processing input data using a machine-learning model having a machine-learning architecture. The computer-implemented system for adapting a machine-learning architecture of a first machine-learning model comprises one or more processors and one or more storage devices. The machine-learning architecture comprises a color image branch configured to process color image data. The color image branch comprises a sequence of convolution blocks. The machine-learning architecture comprises a depth branch configured to process depth data. The depth branch comprises a sequence of convolution blocks. The machine-learning architecture comprises one or more fusing components configured to combine intermediary data of two or more of the branches. Each fusing component is configured to combine an output of a first block of one of the branches and an output of a second block of another branch. An output of the fusing component is used as input of a third block of one of the branches. The third block is a convolution block of one of the sequences of convolution blocks. The machine-learning architecture comprises an output component configured to provide an output of the machine-learning model. The output is based on an output of one or more of the branches. The system is configured to adapt the machine-learning architecture of the first machine-learning model using a second machine-learning model. The second machine-learning model is trained to select, for each of the one or more fusing components, the first block, the second block, and the third block.