公开(公告)号：US20220232198A1

公开(公告)日：2022-07-21

申请号：US17716373

申请日：2022-04-08

申请人： Sony Group Corporation

发明人： Richmond Hicks

IPC分类号： H04N13/271 ,  G06T7/50 ,  H04N5/235 ,  G03B21/00 ,  H04N5/232 ,  G01B11/25 ,  G03B17/54 ,  G06T7/521

摘要： Systems, devices, and techniques related to matching features between a dynamic vision sensor and one or both of a dynamic projector or another dynamic vision sensor are discussed. Such techniques include casting a light pattern with projected features having differing temporal characteristics onto a scene and determining the correspondence(s) based on matching changes in detected luminance and temporal characteristics of the projected features.

公开(公告)号：US20220158498A1

公开(公告)日：2022-05-19

申请号：US17385466

申请日：2021-07-26

申请人： Austin Russell

发明人： Austin Russell

IPC分类号： H02J50/30 ,  H04N13/204 ,  H04N13/207 ,  H04N13/243 ,  H04N13/25 ,  H04N13/254 ,  H04N13/257 ,  H04N13/271 ,  H04N13/296 ,  G03B17/54 ,  G03B35/00 ,  H04N13/363 ,  G01B11/25 ,  G06T19/00

摘要： The systems and methods described herein include a device that can scan the surrounding environment and construct a 3D image, map, or representation of the surrounding environment using, for example, invisible light projected into the environment. In some implementations, the device can also project into the surrounding environment one or more visible radiation pattern patterns (e.g., a virtual object, text, graphics, images, symbols, color patterns, etc.) that are based at least in part on the 3D map of the surrounding environment.

公开(公告)号：US20220148137A1

公开(公告)日：2022-05-12

申请号：US17595838

申请日：2020-05-26

申请人： Abhijith PUNNAPPURATH ,  Michael BROWN

发明人： Abhijith PUNNAPPURATH ,  Michael BROWN

IPC分类号： G06T5/00 ,  H04N13/128 ,  G06T7/194 ,  H04N13/271 ,  H04N5/232 ,  G06T7/50

摘要： A system and method for reflection removal of an image from a dual-pixel sensor. The image including a left view and a right view. The method including: determining a first gradient of the left view and a second gradient of the right view; determining disparity between the first gradient and the second gradient using a sum of squared differences (SSD); determining a confidence value at each pixel using the SSD; determining a weighted gradient map using the confidence values; minimizing a cost function to estimate the background layer, the cost function including the weighted gradient map, wherein the image includes the background layer added to a reflection layer; and outputting at least one of the background layer and the reflection layer.

公开(公告)号：US11330247B2

公开(公告)日：2022-05-10

申请号：US17221443

申请日：2021-04-02

申请人： Sony Group Corporation

发明人： Richmond Hicks

IPC分类号： H04N13/271 ,  G01B11/25 ,  G03B17/54 ,  G03B21/00 ,  G06T7/50 ,  G06T7/521 ,  H04N5/232 ,  H04N5/235 ,  H04N13/00

摘要： Systems, devices, and techniques related to matching features between a dynamic vision sensor and one or both of a dynamic projector or another dynamic vision sensor are discussed. Such techniques include casting a light pattern with projected features having differing temporal characteristics onto a scene and determining the correspondence(s) based on matching changes in detected luminance and temporal characteristics of the projected features.

公开(公告)号：US20220103709A1

公开(公告)日：2022-03-31

申请号：US17547751

申请日：2021-12-10

申请人： ML Netherlands C.V.

发明人： Alexander Ilic ,  Benedikt Koeppel

IPC分类号： H04N1/00 ,  H04N13/271 ,  H04N13/275 ,  G06T19/20 ,  H04N13/221 ,  G06T7/55 ,  G01B11/24 ,  G06T7/73 ,  H04N13/211 ,  B33Y50/00 ,  G06T15/04 ,  G06T17/20

摘要： A smartphone may be freely moved in three dimensions as it captures a stream of images of an object. Multiple image frames may be captured in different orientations and distances from the object and combined into a composite image representing an three-dimensional image of the object. The image frames may be formed into the composite image based on representing features of each image frame as a set of points in a three dimensional depth map. Coordinates of the points in the depth map may be estimated with a level of certainty. The level of certainty may be used to determine which points are included in the composite image. The selected points may be smoothed and a mesh model may be formed by creating a convex hull of the selected points. The mesh model and associated texture information may be used to render a three-dimensional representation of the object on a two-dimensional display. Additional techniques include processing and formatting of the three-dimensional representation data to be printed by a three-dimensional printer so a three-dimensional model of the object may be formed.

公开(公告)号：US11282289B2

公开(公告)日：2022-03-22

申请号：US16933696

申请日：2020-07-20

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Hojung Kim ,  Yongkyu Kim ,  Hoon Song ,  Hongseok Lee

IPC分类号： G06T19/20 ,  G06F17/14 ,  H04N13/271 ,  H04N13/161 ,  G03H1/08 ,  G06T7/262 ,  H04N7/18

摘要： A method for processing a three-dimensional (3D) image includes acquiring a frame of a color image and a frame of a depth image, and generating a frame by combining the acquired frame of the color image with the acquired frame of the depth image. The generating of the frame includes combining a line of the color image with a corresponding line of the depth image.

公开(公告)号：US11282287B2

公开(公告)日：2022-03-22

申请号：US16141630

申请日：2018-09-25

申请人： Matterport, Inc.

发明人： David Alan Gausebeck

IPC分类号： G06T19/20 ,  H04N13/10 ,  H04N13/246 ,  H04N13/204 ,  H04N13/106 ,  H04N13/156 ,  G06T7/521 ,  G06T19/00 ,  G06T17/00 ,  G06T7/593 ,  H04N13/271 ,  G06T7/579 ,  H04N13/00

摘要： The disclosed subject matter is directed to employing machine learning models configured to predict 3D data from 2D images using deep learning techniques to derive 3D data for the 2D images. In some embodiments, a method is provided that comprises receiving, by a system comprising a processor, a panoramic image, and employing, by the system, a three-dimensional data from two-dimensional data (3D-from-2D) convolutional neural network model to derive three-dimensional data from the panoramic image, wherein the 3D-from-2D convolutional neural network model employs convolutional layers that wrap around the panoramic image as projected on a two-dimensional plane to facilitate deriving the three-dimensional data.

公开(公告)号：US11276141B2

公开(公告)日：2022-03-15

申请号：US16986838

申请日：2020-08-06

申请人： SANGMYUNG UNIVERSITY INDUSTRY-ACADEMY COOPERATION FOUNDATION

发明人： Hoon Yoo

IPC分类号： G06T3/00 ,  H04N13/271 ,  G06T5/00

摘要： A lifting transform method performed on an elemental image array may perform a lifting transform on an elemental image array to obtain a difference image (or an error image representing a prediction error) and movement information used for prediction and may appropriately reorder the difference image to obtain a wavelet-type elemental image array.

公开(公告)号：US20220078391A1

公开(公告)日：2022-03-10

申请号：US17526136

申请日：2021-11-15

申请人： Snap Inc.

发明人： Sagi Katz ,  Matan Zohar ,  Ilya Levin

IPC分类号： H04N13/111 ,  G02B27/01 ,  H04N13/271 ,  G06T3/00 ,  G06T7/521

摘要： A virtual wave creation system comprises an eyewear device that includes a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. Execution of programming by a processor configures the virtual wave creation system to generate, for each of multiple initial depth images, a respective wave image by applying a transformation function that is responsive to a selected input parameter to the initial three-dimensional coordinates. The virtual wave creation system creates a warped wave video including a sequence of the generated warped wave images. The virtual wave creation system presents, via an image display, the warped wave video.

公开(公告)号：US20220070436A1

公开(公告)日：2022-03-03

申请号：US17522863

申请日：2021-11-09

申请人： Sony Depthsensing Solutions SA/NV

发明人： Daniel Van Nieuwenhove ,  Julien Thollot

IPC分类号： H04N13/25 ,  H04N13/128 ,  H04N13/243 ,  H04N13/246 ,  H04N13/257 ,  H04N13/271 ,  H04N13/122 ,  H04N13/207 ,  H04N5/341 ,  G01S17/86 ,  G01S17/894

摘要： The invention relates to a TOF camera system comprising several cameras, at least one of the cameras being a TOF camera, wherein the cameras are assembled on a common substrate and are imaging the same scene simultaneously and wherein at least two cameras are driven by different driving parameters.