-
公开(公告)号：US20220309696A1
公开(公告)日：2022-09-29
申请号：US17677365
申请日：2022-02-22
申请人： MEDIATEK INC.
发明人： Ren WANG , Yu-Lun LIU , Yu-Hao HUANG , Ning-Hsu WANG
摘要： A depth estimation from focus method and system includes receiving input image data containing focus information, generating an intermediate attention map by an AI model, normalizing the intermediate attention map into a depth attention map via a normalization function, and deriving expected depth values for the input image data containing focus information from the depth attention map. The AI model for depth estimation can be trained unsupervisedly without ground truth depth maps. The AI model of some embodiments is a shared network estimating a depth map and reconstructing an AiF image from a set of images with different focus positions.
-
公开(公告)号：US11375097B2
公开(公告)日：2022-06-28
申请号：US17136261
申请日：2020-12-29
发明人： Chuan Yang , Yunju Liu , Li-Te Kuo
摘要： A lens control method is applied to a camera module with an OIS motor. The module includes a lens, an OIS motor, an OIS motor driver module, and an imaging sensor. The method includes: obtaining a first speed and a first direction of a to-be-photographed object in a moving process, an object distance between the to-be-photographed object and the lens, and an image distance between the lens and the imaging sensor; calculating a second speed and a second direction based on the first speed, the first direction, the object distance, and the image distance; and sending a control signal to the OIS motor driver module, so that the OIS motor driver module drives the OIS motor to control the lens to move at the second speed and in the second direction.
-
公开(公告)号：US20220189048A1
公开(公告)日：2022-06-16
申请号：US17684470
申请日：2022-03-02
摘要： A method of generating a composite image from multiple images captured for a subject is disclosed. In some embodiments, the method may include receiving, via an image capturing device, a plurality of sets of images of at least a portion of a subject. The images within a set of images may be captured at a plurality of vertical positions with respect to an associated fixed section of a horizontal plane. The method may further include generating a plurality of focus-stacked images corresponding to the plurality of sets of images, for example, by combining the images in the associated set of images. The method may further include aligning the plurality of focus-stacked images in the horizontal plane based on a horizontal coordinate transformation model to generate a composite image representing the subject.
-
公开(公告)号：US11348264B1
公开(公告)日：2022-05-31
申请号：US16856779
申请日：2020-04-23
申请人： Meta Platforms, Inc.
发明人： Tyler Back , Gabriel Molina
摘要： A communication system captures writing surface content in a physical space for transmittal to remote client devices participating in a communication session. During a communication session with one or more remote client devices, a communication system captures image data and depth data describing objects in a physical space of the communication system. Based on the captured data, the communication system identifies a writing surface in the physical space and captures content on the writing surface. The communication system may also identify objects occluding content on the writing surface based on the captured data and may modify image data to make an object occluding the content at least partially transparent. The communication system transmits the content to at least one of the remote client devices participating in the communication session.
-
公开(公告)号：US11308704B2
公开(公告)日：2022-04-19
申请号：US16071072
申请日：2016-01-18
申请人： LG ELECTRONICS INC.
发明人： Eunjeong Ryu , Youngjun Kim , Wonjoo Park
摘要： The present invention relates to a mobile terminal and a control method therefor, the mobile terminal comprising: at least one camera; a display unit placed toward the eyes of a user searing the mobile terminal and for displaying an image, the image comprising one of a VR (virtual reality) image and a 3D image; and a control unit for performing an action related to the image according to a gesture input sensed by the camera, wherein, when a first gesture input proceeding along a first plane opposite to the image is sensed or a second gesture input proceeding along a second plane orthogonal to the first plane is sensed by the camera, the control unit performs an action corresponding to the sensed first or second gesture input, thereby providing the user with an effect of providing more various VR related functions through the first gesture input made on a first plane space opposite to the image visible to the eyes of the user and the second gesture input made on a second plane space orthogonal to the first plane.
-
公开(公告)号：US11302017B2
公开(公告)日：2022-04-12
申请号：US16817081
申请日：2020-03-12
摘要： A method of generating a composite image from multiple images captured for a subject is disclosed. In some embodiments, the method may include receiving, via an image capturing device, a plurality of sets of images of at least a portion of a subject. The images within a set of images may be captured at a plurality of vertical positions with respect to an associated fixed section of a horizontal plane. The method may further include generating a plurality of focus-stacked images corresponding to the plurality of sets of images, for example, by combining the images in the associated set of images. The method may further include aligning the plurality of focus-stacked images in the horizontal plane based on a horizontal coordinate transformation model to generate a composite image representing the subject.
-
公开(公告)号：US11218626B2
公开(公告)日：2022-01-04
申请号：US16010105
申请日：2018-06-15
发明人： Chao Wang , Jizhang Shan
摘要： A method of focusing dual cameras including receiving a fixed focus image from a fixed focus camera module, receiving an auto focus image from an auto focus camera module, calibrating a lens distortion of the auto focus camera module, calibrating a geometric relation of the auto focus camera module and the fixed focus camera module, calculating a depth of focus difference between the fixed focus image and the auto focus image, estimating an auto focus position based on the depth of focus difference and setting the auto focus position based on the estimation.
-
公开(公告)号：US20210352260A1
公开(公告)日：2021-11-11
申请号：US17315269
申请日：2021-05-08
IPC分类号： H04N13/254 , G06T7/571 , H04N13/207 , G02B5/20 , G02B5/00
摘要： Techniques are described for passive three-dimensional image sensing based on referential image blurring. For example, a filter mask is integrated with a lens assembly to provide one or more normal imaging bandpass (NIB) regions and one or more reference imaging bandpass (RIB) regions, the regions being optically distinguishable and corresponding to different focal lengths and/or different focal paths. As light rays from a scene object pass through the different regions of the filter mask, a sensor can detect first and second images responsive to those light rays focused through the NIB region and the RIB region, respectively (according to their respective focal lengths and/or respective focal paths). An amount of blurring between the images can be measured and correlated to an object distance for the scene object. Some embodiments project additional reference illumination to enhance blurring detection in the form of reference illumination flooding and/or spotted illumination.
-
公开(公告)号：US20210335005A1
公开(公告)日：2021-10-28
申请号：US16854977
申请日：2020-04-22
申请人： Dell Products L.P.
摘要： A system, method, and computer-readable medium are disclosed for augmented reality detection of enterprise systems in a data center. Ann augmented reality view is captured of an enterprise system and objects of the enterprise system. Significant areas are detected of the enterprise. In the captured augmented reality view bounding boxes are added around the significant areas. Determination is performed of three-dimensional orientation of the significant areas. Depth of the signification areas is determined based on the three-dimensional orientation.
-
30.发明申请公开(公告)号：US20210312596A1
公开(公告)日：2021-10-07
申请号：US17353539
申请日：2021-06-21
申请人： NIKON CORPORATION
发明人： Tsuneyuki HAGIWARA
摘要： An image processing device includes a first processing unit which executes blurring processing in a common focus position on each of plural images in mutually different focus positions, an integration unit which generates an integrated image resulting from integration of the plural images on which the blurring processing is executed, and a second processing unit which generates a composite image having a predetermined blur degree by executing sharpening processing on the integrated image generated by the integration unit based on information in which optical information indicating optical characteristics of an optical system in which the plural images are acquired and a blur degree of the blurring processing in the common focus position are composited together along a depth direction of the plural image.
-
-
-
-
-
-
-
-
-
搜索结果
388 条记录 (耗时 0.021 秒)
