公开(公告)号：WO2022000040A1

公开(公告)日：2022-01-06

申请号：PCT/AU2021/050704

申请日：2021-06-30

Applicant: SCIMIAN PTY LTD

Inventor： PATERNOSTER, Guven ,  VISSER, Daniel

IPC: G06F3/14 ,  G09G5/12 ,  H04W84/18 ,  H04N21/43 ,  H04W4/02 ,  H04L7/00 ,  G01S19/14 ,  G01S5/0027 ,  G06F3/1438 ,  G06F3/1446 ,  G06T3/4092 ,  G09G2300/026 ,  G09G2360/04 ,  H04L65/1083 ,  H04L65/4015 ,  H04L65/4084 ,  H04L67/10 ,  H04L67/18 ,  H04N21/4302 ,  H04N5/2256 ,  H04N5/268 ,  H04N5/30 ,  H04W4/021 ,  H04W4/08 ,  H04W4/33

Abstract: An image processing system for reproducing an image across an array of nodes, comprising: an array processor for identifying a plurality of nodes and associating the plurality of nodes to form an array, the array for displaying a combined representation of a digital image, the array processor determining the position of each node in the array; a video processor for selecting a digital image for representation across the array and allocating a component part of the digital image to nodes in the array in dependence on the position of the node within the array, such that simultaneous display of the component parts by the nodes produces a representation of the digital image across the array.

公开(公告)号：WO2021258529A1

公开(公告)日：2021-12-30

申请号：PCT/CN2020/111771

申请日：2020-08-27

Applicant: 北京大学深圳研究生院

Inventor： 王荣刚 ,  王振宇 ,  韩冰杰 ,  李旭峰 ,  高文

IPC: G06T3/40 ,  G06N3/08 ,  G06T3/4092 ,  G06T5/001 ,  G06T7/50

Abstract: 本申请公开了一种图像降分辨率及复原方法、设备及可读存储介质，所述图像降分辨率及复原方法包括：获取待处理图像，并确定所述待处理图像对应的图像梯度信息，进而将所述待处理图像输入预设图像降分辨率模型，对所述待处理图像进行降分辨率，获得初始低分辨率图像，进而将所述图像梯度信息存储于所述初始低分辨率图像中，获得目标低分辨率图像，将所述目标低分辨率图像输入预设图像复原模型，以基于所述图像梯度信息，对所述目标低分辨率图像进行高分辨率复原，获得目标复原图像。本申请解决了图像降分辨率后复原精确度低的技术问题。

公开(公告)号：WO2023034633A2

公开(公告)日：2023-03-09

申请号：PCT/US2022/042620

申请日：2022-09-06

Applicant: META PLATFORMS TECHNOLOGIES, LLC

Inventor： CARNEY, Matthew ,  XU, Liang ,  SHEN, Mengnan ,  WOODLAND, David Sven ,  TAO, Xiaohui ,  YIP, Yue Kwen Justin

IPC: G06T11/60 ,  G06T3/40 ,  G06T1/00 ,  G06F3/01 ,  G06F1/16 ,  G06F1/163 ,  G06F1/3203 ,  G06F3/017 ,  G06F3/14 ,  G06T2200/24 ,  G06T3/4092 ,  G09G2320/0626

Abstract: A method for the delayed processing of image data captured by a wrist-wearable device is provided. The method includes receiving, at a wrist-wearable device, image data having a first resolution. The method includes, responsive to receiving the image data having the first resolution, storing the image data on the wrist-wearable device. The method further includes downscaling at least a portion of the image data to produce downscaled image data having a second resolution and presenting, on the wrist-wearable device, the downscaled image data having the second resolution. The method further includes receiving a request to send a representation of the image data to a device distinct from the wrist-wearable device. Responsive to the request, the method includes causing image-processing algorithms to be applied to the stored image data such that processed image data is generated and made available at the distinct device.

公开(公告)号：WO2022221700A2

公开(公告)日：2022-10-20

申请号：PCT/US2022/025079

申请日：2022-04-15

Applicant: METACONSUMER, INC.

Inventor： D'AMICO, Nathaniel ,  RAMASESHAN, Chandrasekhar Vijay

IPC: G06T1/00 ,  G06Q30/00 ,  G06T3/40 ,  G06T3/4092 ,  H04N1/00244

Abstract: A client device assists in identifying user consumption of information. The client device comprises a hardware processor; a screen; memory storing computer instructions that when executed perform capturing a series of screen image snapshots being presented on the screen; reducing resolution of each screen image snapshot in the series of screen image snapshots; capturing metadata associated with each screen image snapshot in the series of screen image snapshots, the metadata at least including a timestamp; identifying a duplicate in the series of screen image snapshots; discarding the duplicate from the series of screen image snapshots; and uploading the series of captured screen image snapshots to a processing server for processing.

公开(公告)号：WO2021251658A1

公开(公告)日：2021-12-16

申请号：PCT/KR2021/006589

申请日：2021-05-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： KIM, Jaehwan ,  PARK, Youngo ,  CHOI, Kwangpyo

IPC: H04N7/14 ,  H04N7/01 ,  G06N3/08 ,  G06T3/0056 ,  G06T3/4046 ,  G06T3/4053 ,  G06T3/4092 ,  H04N7/0102 ,  H04N7/141 ,  H04N7/147

Abstract: Provided is a method of adaptively performing artificial intelligence (AI) downscaling on an image during a video telephone call of a user terminal. The method includes obtaining, from an opposite user terminal, AI upscaling support information of the opposite user terminal that is a target of a video telephone call, determining whether the user terminal is to perform AI downscaling on an original image, based on the AI upscaling support information, based on determining that the user terminal is to perform AI downscaling on the original image, obtaining a first image by AI downscaling the original image using a downscaling deep neural network (DNN), generating image data by performing first encoding on the first image, and transmitting AI data including information related to the AI downscaling and the image data.