公开(公告)号：WO2023085963A1

公开(公告)日：2023-05-19

申请号：PCT/RU2021/000497

申请日：2021-11-12

申请人： HUAWEI TECHNOLOGIES CO., LTD. ,  KHIZBULLIN, Renat Ahmirovich

发明人： OSTYAKOV, Pavel Aleksandrovich ,  KONONYKHIN, Danil Aleksandrovich

IPC分类号： G06T3/40 ,  G06T5/00 ,  G06T11/60

摘要： Described is an apparatus (600) for forming a restored image (102), the apparatus being configured to: receive (501) an initial image (101); form (502) an estimate of text in the initial image (101), the text comprising at least one character; correct (503) the estimate of text using a text correction algorithm to form a corrected text estimate; convert (504) text in the corrected text estimate into a text image; and input (505) the text image and the initial image (101) into a trained artificial intelligence model to thereby form the restored image (102). Utilizing textual information from the initial image may allow for significant improvement in the quality of restored images.

公开(公告)号：WO2023078012A1

公开(公告)日：2023-05-11

申请号：PCT/CN2022/123240

申请日：2022-09-30

申请人： 珠海优特智厨科技有限公司

发明人： 吴甲文 ,  张馨月 ,  刘玫潭 ,  黄烁 ,  彭允胄 ,  谢芳

IPC分类号： G06T11/60 ,  G06Q50/12

摘要： 一种电子菜谱的使用及权限分享方法，包括：接收菜谱分享指令或菜谱分享请求，菜谱分享指令和菜谱分享请求包括分享方和被分享方信息(S202)；根据菜谱分享指令或菜谱分享请求，将分享方拥有的菜谱权限共享或转移至被分享方，其中，菜谱权限包括菜谱的使用权限、使用次数和/或使用时长(S204)。

公开(公告)号：WO2023075936A1

公开(公告)日：2023-05-04

申请号：PCT/US2022/042821

申请日：2022-09-08

申请人： MICROSOFT TECHNOLOGY LICENSING, LLC.

发明人： LI, Ji ,  SUN, Xiao ,  DAI, Qi ,  HU, Han

IPC分类号： G06T7/11 ,  G06T11/60

摘要： A scheme for modifying an image is disclosed, which includes receiving a source image having a first image configuration; determining a second image configuration for a target image; providing the received source image to an AI engine trained to identify, based on a set of rules related to visual features, candidate regions from the source image; generating proposal images based on the candidate regions, respectively; determining, based on prior aesthetical evaluation data, an aesthetical value of each regional proposal image; and selecting, based on the determined aesthetical value of each regional proposal image, one of the regional proposal images as the target image; extracting, from the AI engine, the target image; and causing the target image to be displayed via a display of a user device.

公开(公告)号：WO2023049118A1

公开(公告)日：2023-03-30

申请号：PCT/US2022/044132

申请日：2022-09-20

申请人： INNOVEGA, INC.

发明人： LEGERTON, Jerome A. ,  MARSH, Jay

IPC分类号： A61B3/18 ,  A61B3/10 ,  G06T11/60 ,  A61B3/00

摘要： In general, one aspect disclosed features a computer-implemented method comprising: obtaining a first metric of a physiological aspect of a patient, the first metric obtained at a first time by a head-wearable apparatus while the head-wearable apparatus is worn by the patient; obtaining a second metric of the physiological aspect of a patient, the second metric obtained at a second time by the head-wearable apparatus while the head-wearable apparatus is worn by the patient, wherein the second time is later than the first time; determining a value for a parameter of the head-wearable apparatus based on the first metric and the second metric; and setting the parameter in the head-wearable apparatus to the determined value for the parameter.

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

申请人： META PLATFORMS TECHNOLOGIES, LLC

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

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

摘要： 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：WO2023016150A1

公开(公告)日：2023-02-16

申请号：PCT/CN2022/104273

申请日：2022-07-07

申请人： 北京字跳网络技术有限公司

发明人： 卢智雄

IPC分类号： G06T11/60 ,  G06T7/10

摘要： 本公开实施例提供一种图像处理方法、装置、设备及存储介质。其中图像处理方法包括：获取目标图像，以及获取所述目标图像中天空的属性信息；对所述目标图像进行天空分割处理，得到所述目标图像中的天空图像；基于所述属性信息，对所述目标图像中的天空图像进行相应的特效处理。基于属性信息选择对应的特效处理步骤对天空图像进行特效处理，保证特效处理的效果与目标图像中的天空图像匹配，继而保证了特效添加效果，提高了用户体验。

公开(公告)号：WO2023008671A1

公开(公告)日：2023-02-02

申请号：PCT/KR2022/002090

申请日：2022-02-11

申请人： 주식회사 넥스트칩

发明人： 조성용 ,  나원섭

IPC分类号： G06T11/60 ,  G06T7/70 ,  G06T5/40 ,  G06T3/40 ,  G06V10/46 ,  B60W40/02

摘要： 일 실시예에 따르면, 입력 영상에서 추출된 특징점에 대한 기술자를 생성하기 위해, 입력 영상 내에서 특징점을 기준으로 하는 미리 설정된 크기의 메인 패치에 포함되는 복수의 서브 패치들의 각각의 크기를 결정하고, 복수의 서브 패치들 중 타겟 서브 패치를 구성하는 픽셀들 각각에 대해, 그래디언트의 방향을 계산하고, 그래디언트의 방향을 구분하기 위한 복수의 빈들의 개수를 결정하고, 타겟 서브 패치에 대해, 타겟 서브 패치를 구성하는 픽셀들의 그래디언트의 방향에 기초하여 복수의 빈들에 대한 히스토그램을 생성하고, 히스토그램에 기초하여 특징점에 대한 기술자를 생성할 수 있다. 그 외에도 다양한 실시예들이 가능할 수 있다.

公开(公告)号：WO2023273117A1

公开(公告)日：2023-01-05

申请号：PCT/CN2021/132562

申请日：2021-11-23

申请人： 完美世界（北京）软件科技发展有限公司

发明人： 段文杰

IPC分类号： G06T7/40 ,  A63F13/52 ,  G06T11/60

摘要： 一种地形的渲染方法和装置、计算机设备和存储介质，其中，该方法包括：将多层地形纹理进行混合，得到与多层地形纹理对应的目标虚拟纹理，多层地形纹理为与目标地形对应的地形纹理（S202）；获取与目标虚拟纹理对应的目标映射纹理，目标映射纹理用于存储目标虚拟纹理的纹理空间到目标地形的地形空间的对应信息（S204）；通过对目标虚拟纹理和目标映射纹理进行采样，在目标帧中渲染出目标地形的地形表面（S206）。通过该方法，解决了相关技术中的虚拟纹理的渲染方式存在对设备的渲染性能消耗大的问题。

公开(公告)号：WO2022260386A1

公开(公告)日：2022-12-15

申请号：PCT/KR2022/007982

申请日：2022-06-07

申请人： 주식회사 클레온

发明人： 강지수 ,  최태민

IPC分类号： G06T11/60 ,  G06T7/30 ,  G06V10/46 ,  G06N3/08

摘要： 본 발명은 딥러닝 네트워크를 이용한 배경 및 얼굴 합성 방법 및 장치에 관한 것으로서, 원본 얼굴 이미지 및 변환된 얼굴 이미지를 입력 받아 각각에 대한 데이터 전처리 및 특징 벡터를 추출하고, 추출된 특징 벡터로부터 얼굴 특징 벡터 마스크를 생성하고, 생성된 얼굴 특징 벡터 마스크 기반 적응형 객체 정규화를 수행하여 합성 이미지를 생성하는 것을 특징으로 한다.

公开(公告)号：WO2022241441A1

公开(公告)日：2022-11-17

申请号：PCT/US2022/072260

申请日：2022-05-11

申请人： BAKER HUGHES HOLDINGS LLC

发明人： SHAPIRO, Vladimir ,  WHITING, Ozge Can ,  DHANANI, Taufiq ,  HARE, John ,  ODISIO, Matthias ,  KAIRIUKSTIS, Edvardas

IPC分类号： G06T19/20 ,  G06T17/00 ,  G06T7/70 ,  G06T7/11 ,  G06T7/13 ,  G06V20/70 ,  G06F40/169 ,  G06T11/60 ,  G06T15/205 ,  G06T2219/004

摘要： A method includes receiving data characterizing a two-dimensional target site image including an image of a first asset acquired by a camera. The camera has a first location during the acquisition of the two-dimensional target site image. The method also includes receiving data characterizing a three-dimensional model of a target site that includes a plurality of assets including the first asset. The three-dimensional model is annotated to at least identify the first asset. The method further includes generating a projected annotation of the first asset on the two-dimensional target site image by at least projecting the three-dimensional model based on the first location and orientation of the camera relative to the first asset during the acquisition of the target site image.