-
公开(公告)号：US20230091909A1
公开(公告)日：2023-03-23
申请号：US17588024
申请日：2022-01-28
Applicant: Samsung Electronics Co., Ltd.
Inventor： Pavan Chennagiri , John Seokjun Lee , Hamid R. Sheikh
Abstract: An apparatus includes at least one memory configured to store an AI network and at least one processor. The at least one processor is configured to generate a dead leaves model. The at least one processor is also configured to capture a ground truth frame from the dead leaves. The at least one processor is further configured to apply a mathematical noise model to the ground truth frame to produce a noisy frame. In addition, the at least one processor is configured to train the AI network using the ground truth frame and the noisy frame.
-
公开(公告)号：US20230035482A1
公开(公告)日：2023-02-02
申请号：US17649095
申请日：2022-01-27
Applicant: Samsung Electronics Co., Ltd.
Inventor： John W. Glotzbach , Long N. Le , Zhen Tong , Hamid R. Sheikh , Yibo Xu
Abstract: A method includes obtaining multiple input image frames and determining how to warp at least one of the input image frames. The method also includes performing an intraband demosaic-warp operation to reconstruct image data in different color channels of the input image frames and warp the at least one input image frame to produce RGB input image frames. The method further includes blending the RGB input image frames to produce a blended RGB image frame, performing an interband denoising operation to produce a denoised RGB image frame, and performing an interband sharpening operation to produce a sharpened RGB image frame. In addition, the method includes performing an interband demosaic operation to substantially equalize high-frequency content in different color channels of the sharpened RGB image frame to produce an equalized sharpened RGB image frame and generating a final image of the scene based on the equalized sharpened RGB image frame.
-
公开(公告)号：US11503266B2
公开(公告)日：2022-11-15
申请号：US16811585
申请日：2020-03-06
Applicant: Samsung Electronics Co., Ltd.
Inventor： Kushal Kardam Vyas , Yingmao Li , Chenchi Luo , George Q. Chen , Hamid R. Sheikh , Youngjun Yoo , Michael O. Polley
IPC: H04N13/128 , G06T3/40 , G06T5/00 , G06T5/50 , H04N13/00
Abstract: A method includes obtaining, using at least one processor, first and second input image frames, where the first and second input image frames are associated with first and second image planes, respectively. The method also includes obtaining, using the at least one processor, a depth map associated with the first input image frame. The method further includes producing another version of the depth map by performing one or more times: (a) projecting, using the at least one processor, the first input image frame to the second image plane in order to produce a projected image frame using (i) the depth map and (ii) information identifying a conversion from the first image plane to the second image plane and (b) adjusting, using the at least one processor, at least one of the depth map and the information identifying the conversion from the first image plane to the second image plane.
-
公开(公告)号：US20220198722A1
公开(公告)日：2022-06-23
申请号：US17566320
申请日：2021-12-30
Applicant: Samsung Electronics Co., Ltd.
Inventor： Deboleena Roy , Long N. Le , Hamid R. Sheikh
IPC: G06T11/00 , G06V10/60 , G06T7/55 , G06V10/774 , G06V10/776
Abstract: A method includes capturing a plurality of first images using a first image sensor and capturing a plurality of second images using a second image sensor. The method also includes estimating depth information based on at least one of the first images and at least one of the second images. The method further includes obtaining information related to a lighting direction from an artificial intelligence (AI) light director, where the AI light director is trained to determine one or more lighting directions. In addition, the method includes generating at least one relit image using at least one of the first and second images based on the obtained information related to the lighting direction and the estimated depth information.
-
15.发明授权公开(公告)号：US11107191B2
公开(公告)日：2021-08-31
申请号：US16278567
申请日：2019-02-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： Omar A. Elgendy , John W. Glotzbach , Hamid R. Sheikh
Abstract: A method includes obtaining multiple image frames of a scene using at least one camera of an electronic device and processing the multiple image frames to generate a higher-resolution image of the scene. Processing the multiple image frames includes generating an initial estimate of the scene based on the multiple image frames. Processing the multiple image frames also includes, in each of multiple iterations, (i) generating a current estimate of the scene based on the image frames and a prior estimate of the scene and (ii) regularizing the generated current estimate of the scene. The regularized current estimate of the scene from one iteration represents the prior estimate of the scene in a subsequent iteration. The iterations continue until the estimates of the scene converge on the higher-resolution image of the scene.
-
Patent Agency Ranking
16.发明授权公开(公告)号：US11062436B2
公开(公告)日：2021-07-13
申请号：US16572227
申请日：2019-09-16
Applicant: Samsung Electronics Co., Ltd.
Inventor： Ibrahim Pekkucuksen , Hamid R. Sheikh , John W. Glotzbach
Abstract: A method for multi-frame blending includes obtaining at least two image frames of a scene. One of the image frames is associated with a shorter exposure time and a higher sensitivity and representing a reference image frame. At least one other of the image frames is associated with a longer exposure time and a lower sensitivity and representing at least one non-reference image frame. The method also includes blending the reference and non-reference image frames into a blended image such that (i) one or more motion regions of the blended image are based more on the reference image frame and (ii) one or more stationary regions of the blended image are based more on the at least one non-reference image frame.
-
公开(公告)号：US20200186710A1
公开(公告)日：2020-06-11
申请号：US16704982
申请日：2019-12-05
Applicant: Samsung Electronics Co., Ltd.
Inventor： Hamid R. Sheikh , Youngjun Yoo , Seok-Jun Lee , Michael O. Polley
Abstract: A method includes, in a first mode, positioning first and second tiltable image sensor modules of an image sensor array of an electronic device so that a first optical axis of the first tiltable image sensor module and a second optical axis of the second tiltable image sensor module are substantially perpendicular to a surface of the electronic device, and the first and second tiltable image sensor modules are within a thickness profile of the electronic device. The method also includes, in a second mode, tilting the first and second tiltable image sensor modules so that the first optical axis of the first tiltable image sensor module and the second optical axis of the second tiltable image sensor module are not perpendicular to the surface of the electronic device, and at least part of the first and second tiltable image sensor modules are no longer within the thickness profile of the electronic device.
-
18.发明授权公开(公告)号：US10554890B1
公开(公告)日：2020-02-04
申请号：US16278581
申请日：2019-02-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： Long N. Le , John W. Glotzbach , Hamid R. Sheikh , Michael O. Polley
Abstract: A method includes capturing multiple pairs of images of a scene at different exposures using at least one camera of an electronic device. Each pair of images includes (i) an ambient image of the scene captured without using a flash of the electronic device and (ii) a flash image of the scene captured using the flash of the electronic device. The method also includes rendering a final image of the scene with a bokeh that is determined using the multiple pairs of images. One of the ambient images or the flash images are captured in order of increasing exposure time, and the other of the ambient images or the flash images are captured in order of decreasing exposure time. The method may also include estimating a depth map associated with the scene using the pairs of images, where the bokeh is based on the depth map.
-
公开(公告)号：US20190246130A1
公开(公告)日：2019-08-08
申请号：US15892141
申请日：2018-02-08
Applicant: Samsung Electronics Co., Ltd.
Inventor： Hamid R. Sheikh , Youngjun Yoo , Michael Polley , Chenchi Luo , David Liu
IPC: H04N19/48 , H04N19/44 , H04N19/11 , H04N19/167
CPC classification number: H04N19/48 , H04N19/11 , H04N19/167 , H04N19/44
Abstract: Methods and systems for compressed domain progressive application of computer vision techniques. A method for decoding video data includes receiving a video stream that is encoded for multi-stage decoding. The method includes partially decoding the video stream by performing one or more stages of the multi-stage decoding. The method includes determining whether a decision for a computer vision system can be identified based on the partially decoded video stream. Additionally, the method includes generating the decision for the computer vision system based on decoding of the video stream. A system for encoding video data includes a processor configured to receive the video data from a camera, encode the video data received from the camera into a video stream for consumption by a computer vision system, and include metadata with the encoded video stream to indicate whether a decision for the computer vision system can be identified from the metadata.
-
公开(公告)号：US20180192098A1
公开(公告)日：2018-07-05
申请号：US15862465
申请日：2018-01-04
Applicant: Samsung Electronics Co., Ltd.
Inventor： Ibrahim E. Pekkucuksen , John Glotzbach , Hamid R. Sheikh , Rahul Rithe
IPC: H04N21/2343 , G06K9/00 , H04N19/543 , G06K9/62 , G06T5/00
CPC classification number: H04N21/234345 , G06K9/00234 , G06K9/4652 , G06K9/6211 , G06K9/6289 , G06T5/002 , G06T5/003 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20012 , G06T2207/20028 , G06T2207/20221 , G06T2207/30196 , G06T2207/30236 , H04N5/23254 , H04N5/23267 , H04N5/2329 , H04N7/0117 , H04N19/543
Abstract: A method and device for blending multiple related frames into a single frame to reduce noise is disclosed. A method includes comparing an input frame to a corresponding reference frame in order to determine if at least one object that is in both frames moves in the input frame, and also to determine edge strengths of the at least one object. The method further includes, based on the comparison, determining which regions of the input frame to blend with corresponding regions of the reference frame, which regions of the input frame not to blend with corresponding regions of the reference frame, and which regions of the input frame to partially blend with corresponding regions of the reference frame.
-
-
-
-
-
-
-
-
-
Search Results
109
records
(took 0.031 seconds)
