公开(公告)号：EP4392936A2

公开(公告)日：2024-07-03

申请号：EP22862084.5

申请日：2022-08-25

申请人： PassiveLogic, Inc.

发明人： MEINERS, Justin

IPC分类号： G06T17/05 ,  G01B11/02 ,  G01B11/22 ,  G06T7/55 ,  G06T7/77

CPC分类号： G06T19/006 ,  G06T17/00 ,  G06T2210/0420130101 ,  G06T2219/00420130101 ,  G06V20/64 ,  G06V10/25 ,  G06N20/00

公开(公告)号：EP4386674A2

公开(公告)日：2024-06-19

申请号：EP24173503.4

申请日：2019-07-18

申请人： Panasonic Intellectual Property Management Co., Ltd.

发明人： AZUMA, Takeo ,  SATO, Satoshi ,  WAKAI, Nobuhiko ,  YOSHIOKA, Kohsuke ,  SHIMIZU, Noritaka ,  KAWAI, Yoshinao ,  AMADA, Takaaki ,  KAWAI, Yoko ,  MURAI, Takeshi ,  TAKEUCHI, Hiroki

IPC分类号： G06T7/55

CPC分类号： G06T7/55 ,  G06T2207/1004820130101 ,  G06T5/50 ,  G06T2200/0420130101 ,  G06T2207/2008120130101 ,  G06T2207/1002420130101 ,  G06T2207/1002820130101 ,  G06T2207/2008420130101

摘要： A depth acquisition device (1) capable of accurately acquiring a depth to a subject includes a memory (200) and a processor (110a) performing: acquiring, from the memory (200), intensities of infrared light measured by imaging with infrared light emitted from a light source and reflected on the subject by pixels in an imaging element; generating a depth image by calculating the distance for each pixel based on the intensities; acquiring, from the memory (200), a visible light image generated by imaging, with visible light, the substantially same scene from the substantially same viewpoint at the substantially same timing as those of the infrared light image generated by imaging based on the intensities; detecting a lower reflection region showing an object having a lower reflectivity from the infrared light image in accordance with the infrared light image and the visible light image; correcting a lower reflection region in the depth image corresponding to the lower reflection region in accordance with the visible light image; and outputting the depth image with the corrected lower reflection region.

公开(公告)号：EP4339890A3

公开(公告)日：2024-06-19

申请号：EP24155243.9

申请日：2019-08-29

申请人： Artec Europe S.à r.l.

发明人： SHARAPOV, Alexander Alexandrovich ,  SUKHOVEY, Sergey Vladimirovich ,  GUSEV, Gleb Alexandrovich ,  YUKHIN, Artem Leonidovich

IPC分类号： G01B11/00 ,  G01B11/25 ,  G06T7/521 ,  G06T7/55

CPC分类号： G01B11/25 ,  G01B11/002 ,  G01B2210/5220130101 ,  G06T7/55 ,  G06T2200/2420130101 ,  G06T2207/1001620130101 ,  G06T2207/1002820130101 ,  G06T7/521

摘要： A three-dimensional (3D) scanner, which is in communication with a display, includes one or more optical sensors. The scanner scans, using the one or more optical sensors, an object having a surface. The scanning generates data corresponding to a 3D shape of at least a portion of the surface of the object. The scanner generates a 3D reconstruction of the shape of the surface of the object. The scanner provides a preview of the 3D reconstruction of the at least portion of the shape of the surface of the object. The scanner provides, to the display, for rendering with the preview of the 3D reconstruction of the at least portion of the shape of the surface of the object, an indication of at least one of a quantity or a quality of the data corresponding to the 3D shape of the at least portion of the surface of the object.

公开(公告)号：EP4365683A1

公开(公告)日：2024-05-08

申请号：EP23207459.1

申请日：2023-11-02

申请人： Fondation B-COM

发明人： MADALI, Nabil ,  GILLES, Antonin ,  GIOIA, Patrick ,  MORIN, Luce

IPC分类号： G03H1/08 ,  G06N3/02 ,  G06N3/0464 ,  G06T7/55 ,  G06N3/08 ,  G06V10/44 ,  G06V10/77 ,  G06V20/64

CPC分类号： G06T7/55 ,  G06V10/7715 ,  G06V20/647 ,  G06N3/0464 ,  G06V10/454 ,  G03H1/0808 ,  G03H1/0866 ,  G03H2001/088320130101 ,  G03H2210/45420130101 ,  G06N3/08

摘要： La présente invention concerne un procédé d'estimation d'une carte de profondeur (C) associée à un hologramme représentant une scène, le procédé comprenant des étapes de :
- reconstruction (E4) d'images (Ii) de la scène, chaque image étant associée à une profondeur (zi),
- décomposition (E6) de chaque image en une pluralité d'imagettes (Ji;j,k) adjacentes les unes aux autres, chaque imagette étant associée à ladite profondeur et comprenant une pluralité de pixels,
- détermination (E8), pour chaque imagette, d'une carte de focalisation (Ci;j,k) par fourniture, en entrée d'un réseau de neurones, des valeurs associées auxdits pixels de l'imagette, pour obtenir, en sortie dudit réseau, ladite carte de focalisation comprenant un niveau de focalisation associé au pixel concerné, et
- détermination (E10) d'une valeur de profondeur, pour chaque point d'une carte de profondeur (C), en fonction des niveaux de focalisation obtenus.
L'invention concerne également un dispositif d'estimation et un programme d'ordinateur associé.

公开(公告)号：EP4348577A1

公开(公告)日：2024-04-10

申请号：EP22733314.3

申请日：2022-05-25

申请人： Koninklijke Philips N.V.

发明人： VAREKAMP, Christiaan

IPC分类号： G06T7/13 ,  G06T7/136 ,  G06T7/194 ,  G06T15/00 ,  G06T17/00 ,  G06T7/55 ,  H04N13/10

公开(公告)号：EP4343698A1

公开(公告)日：2024-03-27

申请号：EP22827279.5

申请日：2022-05-19

申请人： Huawei Technologies Co., Ltd.

发明人： HE, Yong ,  CAI, Bo ,  XU, Lisheng

IPC分类号： G06T7/55

摘要： This application provides a modeling method, a related electronic device, and a storage medium, and relates to the field of three-dimensional reconstruction. In the method, a terminal device may display a first interface including a taken picture; collect a plurality of frames of images corresponding to a to-be-modeled target object in response to a collection operation, and obtain an association relationship between the plurality of frames of images; and obtain a three-dimensional model corresponding to the target object based on the plurality of frames of images and the association relationship between the plurality of frames of images, and display the three-dimensional model. When the plurality of frames of images are collected, a first virtual bounding body including a plurality of patches is displayed. When the terminal device is in a first pose, the terminal device collects a first image, and changes a display effect of a patch corresponding to the first image. When the terminal device is in a second pose, the terminal device collects a second image, and changes a display effect of a patch corresponding to the second image. After changing display effects of the plurality of patches, the terminal device obtains the association relationship between the plurality of frames of images based on the plurality of patches. This method simplifies a 3D modeling process and has low requirements on device hardware.

公开(公告)号：EP4338130A1

公开(公告)日：2024-03-20

申请号：EP23721916.7

申请日：2023-04-25

申请人： VoxelSensors SRL

发明人： VAN DER TEMPEL, Ward ,  MOURAD, Christian

IPC分类号： G06T7/73 ,  G06T7/55

公开(公告)号：EP4315248A1

公开(公告)日：2024-02-07

申请号：EP22722587.7

申请日：2022-03-29

申请人： META PLATFORMS TECHNOLOGIES, LLC

发明人： JIANG, Hao ,  ITHAPU, Vamsi Krishna

IPC分类号： G06T7/70 ,  G06T7/55 ,  G02B27/01

公开(公告)号：EP4293623A1

公开(公告)日：2023-12-20

申请号：EP22770331.1

申请日：2022-03-07

申请人： Huawei Technologies Co., Ltd.

发明人： GONG, Yue ,  MA, Xinjun ,  HE, Jianan ,  CHEN, Lei ,  YU, Fan

IPC分类号： G06T7/55 ,  G06T7/50 ,  G06T15/00 ,  G06T17/00

摘要： This application relates to the field of image processing technologies, and specifically, to an image depth prediction method and an electronic device. The method includes: obtaining a primary view and a first secondary view, where the primary view includes a first pixel, the first pixel corresponds to a second pixel at a first assumed depth, and the second pixel is located on the first secondary view; updating feature information of the second pixel based on the feature information of the second pixel and feature information of at least one third pixel, the fourth pixel is a pixel that corresponds to the first pixel at a second assumed depth and that is on the first secondary view; and obtaining a probability of the first assumed depth based on the feature information of the first pixel and the updated feature information of the second pixel. In the method, features of pixels between adjacent sampling points may be aggregated to features of nearby sampling points, and a possibility that a corresponding assumed depth is a real depth of a pixel in a primary view is determined accordingly, so that accuracy of depth prediction is improved.

公开(公告)号：EP4283562A1

公开(公告)日：2023-11-29

申请号：EP23151516.4

申请日：2023-01-13

申请人： Sichuan Zhong Sheng Matrix Technology Development Co., Ltd.

发明人： CHEN, Zhengquan

IPC分类号： G06T7/55 ,  G06T17/00 ,  H04N13/10 ,  H04N23/90

摘要： The present invention relates to the field of three-dimensional images, and provides a method for three-dimensional reconstruction of a target object, comprising the following steps: calculating and acquiring a visual angle boundary of the target object; acquiring image information of the target object under multiple visual angles in the visual angle boundary, the image information including initial image information and/or fused image information; finishing three-dimensional reconstruction of the target object according to the acquired image information. By adopting the method for three-dimensional reconstruction of the target object in the present invention, three-dimensional reconstruction of the three-dimensional target at different moments can be carried out in real time, no other links are carried out during the operation, the acquired image information is not lost, real information is directly reproduced, and three-dimensional reconstruction of the real target object is realized.