公开(公告)号：US12096121B2

公开(公告)日：2024-09-17

申请号：US18417282

申请日：2024-01-19

申请人： 4D Intellectual Properties, LLC

发明人： James E. Retterath

IPC分类号： H04N23/67 ,  G01S7/4863 ,  G01S17/18 ,  G01S17/894 ,  G01S17/931 ,  H04N13/204 ,  H04N13/257 ,  H04N13/271 ,  H04N13/296

CPC分类号： H04N23/671 ,  G01S7/4863 ,  G01S17/18 ,  G01S17/894 ,  G01S17/931 ,  H04N13/204 ,  H04N13/257 ,  H04N13/271 ,  H04N13/296 ,  H04N2213/005

摘要： Geiger mode photo diodes are solid state photodetectors that are able to detect single photons. Such Geiger mode photo diodes are also referred to as single-photon detectors (SPDs). An array of SPDs can be used as a single detector element in an active sensing system, but sensor systems based on SPD arrays have at least two shortcomings due to ambient light. First, solar background light can hamper the ability to accurately determine depth. Second, ambient light impacts the reflectivity precision because of challenges differentiating between reflected light and ambient light. Embodiments enable active sensors that remove the ambient signal from a sensor's optical input. Other embodiments produce sensor intensity values that have higher precision than typical SPD array devices. Further embodiments produce sensor depth values that have higher precision than typical SPD array devices.

公开(公告)号：US12081721B2

公开(公告)日：2024-09-03

申请号：US17807508

申请日：2022-06-17

申请人： Adeia Imaging LLC

发明人： Kartik Venkataraman ,  Dan Lelescu ,  Jacques Duparre

IPC分类号： H04N13/128 ,  G01C11/06 ,  G02B27/01 ,  G06T7/593 ,  H04N13/243 ,  H04N13/271 ,  H04N23/45 ,  H04N23/90 ,  H04N5/222 ,  H04N13/00 ,  H04N23/11 ,  H04N23/56

CPC分类号： H04N13/128 ,  G01C11/06 ,  G02B27/017 ,  G02B27/0172 ,  G06T7/593 ,  H04N13/243 ,  H04N13/271 ,  H04N23/45 ,  H04N23/90 ,  G02B2027/0136 ,  G02B2027/0138 ,  G02B2027/014 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/20016 ,  H04N5/2226 ,  H04N2013/0081 ,  H04N23/11 ,  H04N23/56

摘要： Embodiments of the invention provide a camera array imaging architecture that computes depth maps for objects within a scene captured by the cameras, and use a near-field sub-array of cameras to compute depth to near-field objects and a far-field sub-array of cameras to compute depth to far-field objects. In particular, a baseline distance between cameras in the near-field subarray is less than a baseline distance between cameras in the far-field sub-array in order to increase the accuracy of the depth map. Some embodiments provide an illumination near-IR light source for use in computing depth maps.

公开(公告)号：US20240276115A1

公开(公告)日：2024-08-15

申请号：US18644152

申请日：2024-04-24

申请人： Corephotonics Ltd.

发明人： Nadav Geva ,  Michael Scherer ,  Ephraim Goldenberg ,  Gal Shabtay

IPC分类号： H04N25/705 ,  G06T7/593 ,  H04N13/207 ,  H04N13/271 ,  H04N25/75

CPC分类号： H04N25/705 ,  G06T7/593 ,  H04N13/207 ,  H04N13/271 ,  H04N25/75

摘要： Indirect time-of-flight (i-ToF) image sensor pixels, i-ToF image sensors including such pixels, stereo cameras including such image sensors, and sensing methods to obtain i-ToF detection and phase detection information using such image sensors and stereo cameras. An i-ToF image sensor pixel may comprise a plurality of sub-pixels, each sub-pixel including a photodiode, a single microlens covering the plurality of sub-pixels and a read-out circuit for extracting i-ToF phase signals of each sub-pixel individually.

公开(公告)号：US12056837B2

公开(公告)日：2024-08-06

申请号：US17654989

申请日：2022-03-15

申请人： Matterport, Inc.

发明人： David Alan Gausebeck

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

CPC分类号： G06T19/20 ,  G06T7/521 ,  G06T7/579 ,  G06T7/593 ,  G06T17/00 ,  G06T19/006 ,  H04N13/10 ,  H04N13/106 ,  H04N13/156 ,  H04N13/204 ,  H04N13/246 ,  H04N13/271 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10052 ,  G06T2210/04 ,  H04N2013/0081 ,  H04N2213/001

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：US12010286B2

公开(公告)日：2024-06-11

申请号：US17942863

申请日：2022-09-12

申请人： Snap Inc.

发明人： Sagi Katz

IPC分类号： H04N13/122 ,  H04N13/128 ,  H04N13/239 ,  H04N13/271 ,  H04N13/344

CPC分类号： H04N13/122 ,  H04N13/128 ,  H04N13/239 ,  H04N13/271 ,  H04N13/344

摘要： Systems and methods for determining disparity between two images are disclosed. Such systems and methods include obtaining a first pixel image of a scene from a first viewpoint, obtaining a second pixel image of the scene from a second viewpoint (e.g., separate from the first viewpoint in a camera baseline direction such as horizontal or vertical), modifying the first and second pixel images using component-separated correction to create respective first and second corrected pixel images maintaining pixel scene correspondence in the camera baseline direction from between the first and second pixel images to between the first and second corrected pixel images, determining pixel pairs from corresponding pixels between the first and second corrected pixel images in the camera baseline direction, and determining disparity correspondence for each of the determined pixel pairs from pixel locations in the first and second pixel images corresponding to respective pixel locations of the pixel pairs in the first and second corrected pixel images.

公开(公告)号：US12007680B2

公开(公告)日：2024-06-11

申请号：US17484723

申请日：2021-09-24

申请人： Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.

发明人： Frank Wippermann ,  Jacques Duparré

IPC分类号： H04N13/271 ,  G02B26/08 ,  G03B35/04 ,  H04N13/239 ,  H04N23/51 ,  H04N23/55 ,  H04N23/56 ,  H04N23/67

CPC分类号： G03B35/04 ,  G02B26/0816 ,  H04N13/239 ,  H04N13/271 ,  H04N23/51 ,  H04N23/55 ,  H04N23/56 ,  H04N23/67

摘要： An inventive device includes a multi-aperture imaging device comprising an image sensor; an array of adjacently arranged optical channels, each optical channel including an optic for projecting at least one partial field of view of a total field of view onto an image sensor area of the image sensor arrangement, a beam deflection means for deflecting an optical path of the optical channels, and a focusing means for setting a focal position of the multi-aperture imaging device. The device further comprises a control means configured to control the focusing means and to receive image information from the image sensor; the control means being configured to control the multi-aperture imaging device into a sequence of focal positions so as to capture a corresponding sequence of image information of the total field of view and to produce, from the sequence of image information, a depth map for the captured total field of view.

公开(公告)号：US11989822B2

公开(公告)日：2024-05-21

申请号：US18338240

申请日：2023-06-20

申请人： Fyusion, Inc.

发明人： Stefan Johannes Josef Holzer ,  Abhishek Kar ,  Matteo Munaro ,  Pavel Hanchar ,  Radu Bogdan Rusu ,  Santi Arano

IPC分类号： G06T7/70 ,  G01C21/32 ,  G06F9/451 ,  G06F16/29 ,  G06F17/18 ,  G06F30/15 ,  G06N3/02 ,  G06Q30/02 ,  G06T7/00 ,  G06T7/593 ,  G06T15/10 ,  G06T15/20 ,  G06T17/00 ,  G06T19/00 ,  H04N13/243 ,  H04N13/271 ,  H04N23/63 ,  H04N13/00

CPC分类号： G06T15/205 ,  G01C21/32 ,  G06F9/453 ,  G06F16/29 ,  G06F17/18 ,  G06F30/15 ,  G06N3/02 ,  G06Q30/0278 ,  G06T7/0002 ,  G06T7/0004 ,  G06T7/593 ,  G06T7/70 ,  G06T15/10 ,  G06T17/00 ,  G06T19/003 ,  G06T19/006 ,  H04N13/243 ,  H04N13/271 ,  H04N23/633 ,  G06T2200/08 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20224 ,  G06T2207/30108 ,  G06T2207/30244 ,  G06T2207/30248 ,  H04N2013/0081

摘要： A plurality of images may be analyzed to determine an object model. The object model may have a plurality of components, and each of the images may correspond with one or more of the components. Component condition information may be determined for one or more of the components based on the images. The component condition information may indicate damage incurred by the object portion corresponding with the component.

公开(公告)号：US11962745B2

公开(公告)日：2024-04-16

申请号：US17763757

申请日：2020-09-29

申请人： INTERDIGITAL CE PATENT HOLDINGS, SAS

发明人： Didier Doyen ,  Franck Galpin ,  Guillaume Boisson

IPC分类号： H04N13/178 ,  G06T7/593 ,  H04N13/194 ,  H04N13/243 ,  H04N13/271 ,  H04N13/282 ,  H04N19/513 ,  H04N19/597 ,  H04N19/70

CPC分类号： H04N13/178 ,  G06T7/596 ,  H04N13/194 ,  H04N13/243 ,  H04N13/271 ,  H04N13/282 ,  H04N19/513 ,  H04N19/597 ,  H04N19/70

摘要： A method and system are provided for processing image content. The method comprises receiving information about a content image captured at least by one camera. The content includes multi-view representation of an image including both distorted and undistorted areas. The camera parameters and image parameters are then obtained and used to determine to which areas are undistorted and which areas are distorted in said image. This is used to calculate depth map of the image using the determined undistorted and distorted information. A final stereoscopic image is then rendered that uses the distorted and undistorted areas and calculation of depth map.

公开(公告)号：US11920916B1

公开(公告)日：2024-03-05

申请号：US17569480

申请日：2022-01-05

申请人： Meta Platforms Technologies, LLC

发明人： Michael Hall ,  Xinqiao Liu

IPC分类号： G01C3/08 ,  G01B11/22 ,  G01S7/4865 ,  H04N13/271

CPC分类号： G01B11/22 ,  G01S7/4865 ,  H04N13/271

摘要： A depth camera assembly (DCA) includes a light generator emitting a beam of light into a local area and a detector. The detector captures light from the beam reflected by objects in the local area to a portion of an array of pixels that each include a single photon avalanche diode (SPAD). The location of the portion of the array is based in part on the angle of the beam emitted from the projector. The DCA identifies a set of pixels of the array corresponding to the portion and selectively retrieves current generated from the reflected light by the pixels in the portion of the array without retrieving current generated by pixels in other portions of the array.

公开(公告)号：US20240062463A1

公开(公告)日：2024-02-22

申请号：US17766715

申请日：2020-10-15

申请人： Dimension Stream Labs AB

发明人： Ulf Assarsson ,  Sverker Rasmuson ,  Erik Sintorn

IPC分类号： G06T17/20 ,  H04N13/271 ,  G06T15/06 ,  G06T5/00 ,  G06T3/40 ,  H04N13/239 ,  H04N13/246 ,  G06T7/73 ,  H04N13/15

CPC分类号： G06T17/20 ,  H04N13/271 ,  G06T15/06 ,  G06T5/006 ,  G06T3/4007 ,  H04N13/239 ,  H04N13/246 ,  G06T7/73 ,  H04N13/15 ,  G06T2200/04

摘要： The present invention relates to a method of real-time generation of a 3D geometry of an object. The method comprises the steps of calibrating at least one RGB camera pair arranged to provide images of the object, receiving input images of the object from the at least on RGB camera pair, and performing a stereo reconstruction in a first hierarchical level using the input images. The stereo reconstruction step further comprises the steps of a) performing a ray marching operation in a first resolution on the input images to determine geometry positions along each view ray of the images; b) applying a uniqueness criterion to the geometry positions; c) determining a normal for each geometry position; d) performing a regularization operation based on the geometry positions and the respective normal, providing updated geometry positions; and e) performing an interpolation operation on the updated geometry positions and respective normal. The method further comprises repeating steps a) and c)-e) in at least one iteration in at least one ascending hierarchical level, wherein the resolution in the ray marching operation is doubled for each iteration, resulting in a geometry buffer for each of the at least one camera pair. The present invention further relates to a 3D image generation device and a system comprising such device.