-
公开(公告)号:US10805649B2
公开(公告)日:2020-10-13
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 , G06K9/62 , G06T5/00 , H04N19/543 , G06K9/46 , H04N5/232 , H04N7/01 , G06T5/50
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.
-
82.
公开(公告)号:US20200267299A1
公开(公告)日:2020-08-20
申请号:US16278543
申请日:2019-02-18
Applicant: Samsung Electronics Co., Ltd.
Inventor: Long N. Le , Hamid R. Sheikh , John W. Glotzbach
Abstract: A method includes capturing multiple ambient images of a scene using at least one camera of an electronic device and without using a flash of the electronic device. The method also includes capturing multiple flash images of the scene using the at least one camera of the electronic device and during firing of a pilot flash sequence using the flash. The method further includes analyzing multiple pairs of images to estimate exposure differences obtained using the flash, where each pair of images includes one of the ambient images and one of the flash images that are both captured using a common camera exposure and where different pairs of images are captured using different camera exposures. In addition, the method includes determining a flash strength for the scene based on the estimate of the exposure differences and firing the flash based on the determined flash strength.
-
公开(公告)号:US12200398B2
公开(公告)日:2025-01-14
申请号:US17591040
申请日:2022-02-02
Applicant: Samsung Electronics Co., Ltd.
Inventor: Gyeongmin Choe , Yingmao Li , John Seokjun Lee , Hamid R. Sheikh , Michael O. Polley
IPC: H04N7/01 , G06T1/00 , G06T3/18 , G06T5/50 , G06T7/207 , H04N1/32 , H04N19/139 , H04N19/577
Abstract: An apparatus includes at least one processing device configured to obtain input frames from a video. The at least one processing device is also configured to generate a forward flow from a first input frame to a second input frame and a backward flow from the second input frame to the first input frame. The at least one processing device is further configured to generate an occlusion map at an interpolated frame coordinate using the forward flow and the backward flow. The at least one processing device is also configured to generate a consistency map at the interpolated frame coordinate using the forward flow and the backward flow. In addition, the at least one processing device is configured to perform blending using the occlusion map and the consistency map to generate an interpolated frame at the interpolated frame coordinate.
-
公开(公告)号:US20240221130A1
公开(公告)日:2024-07-04
申请号:US18149714
申请日:2023-01-04
Applicant: Samsung Electronics Co., Ltd.
Inventor: Nguyen Thang Long Le , Tyler Luu , Hamid R. Sheikh
CPC classification number: G06T5/002 , G06T3/0093 , G06T5/006 , G06T5/50 , G06T2207/20212
Abstract: A method includes generating alignment maps for a first image frame having a first exposure level and a second image frame having a second exposure level different than the first exposure level. The method also includes generating, for the second image frame and a third image frame having a third exposure level different than the first and second exposure levels, shadow maps, saturation maps, and multi-exposure (ME) motion maps based on the alignment maps. The method further includes determining, based on the shadow maps, saturation maps, and ME motion maps, whether to perform machine learning-based denoising and, if so, on which image frame(s) to perform the machine learning-based denoising. In addition, the method includes updating at least one saturation map and at least one ME motion map for at least one of the second and third image frames depending on the image frame(s) on which the denoising is to be performed.
-
公开(公告)号:US11961206B2
公开(公告)日:2024-04-16
申请号:US17651226
申请日:2022-02-15
Applicant: Samsung Electronics Co., Ltd.
Inventor: Kaimo Lin , Hamid R. Sheikh
IPC: G06T3/40 , G06T3/4015 , G06T5/00 , H04N23/73 , H04N23/951
CPC classification number: G06T3/4015 , G06T5/009 , H04N23/73 , H04N23/951
Abstract: A method includes obtaining a Bayer input image. The method also includes generating, using at least one processing device of an electronic device, multiple YUV image frames based on the Bayer input image using non-linear scaling, where the YUV image frames are associated with different exposure settings. The method further includes generating, using the at least one processing device of the electronic device, a fused image based on the YUV image frames. In addition, the method includes applying, using the at least one processing device of the electronic device, global tone-mapping to the fused image in order to generate a tone-mapped fused image, where the global tone-mapping is based on a first cubic spline curve.
-
公开(公告)号:US11869118B2
公开(公告)日:2024-01-09
申请号:US17588024
申请日:2022-01-28
Applicant: Samsung Electronics Co., Ltd.
Inventor: Pavan Chennagiri , John Seokjun Lee , Hamid R. Sheikh
CPC classification number: G06T11/001 , G06N20/00 , G06T5/002 , G06T7/90 , G06T17/00 , G06T19/20 , G06T2207/10012 , G06T2207/10024 , G06T2207/20081 , G06T2219/2012
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.
-
87.
公开(公告)号:US20230362497A1
公开(公告)日:2023-11-09
申请号:US18354409
申请日:2023-07-18
Applicant: Samsung Electronics Co., Ltd.
Inventor: Yibo Xu , Hamid R. Sheikh
CPC classification number: H04N23/80 , H04N23/76 , H04N23/84 , G06F1/1686
Abstract: A method includes obtaining an image, where the image includes one or more frames. The method also includes performing multi-frame processing and image signal processing on the image to produce a processed image. The method further includes performing image restoration on the processed image to produce an output image. Performing the image restoration includes generating a dither signal, applying a dither signal corner attenuation to the dither signal in order to generate an attenuated dither signal, combining the attenuated dither signal with a sharpened denoised signal in order to generate a combine signal, and applying a halo suppression on the combined signal.
-
88.
公开(公告)号:US20230252611A1
公开(公告)日:2023-08-10
申请号:US18046117
申请日:2022-10-12
Applicant: Samsung Electronics Co., Ltd.
Inventor: Gunawath Dilshan Godaliyadda , John W. Glotzbach , Hamid R. Sheikh
CPC classification number: G06T5/009 , G06T5/20 , G06T5/002 , G06T2207/20208
Abstract: A method includes obtaining an image and a gain map associated with the image. The method also includes identifying image patches in the image and corresponding gain map patches in the gain map. Different image patches are centered around different anchor points in the image. The method further includes, for each image patch and its corresponding gain map patch, generating an intensity-gain curve for the associated anchor point. The intensity-gain curve specifies (i) gain values based on the corresponding gain map patch for intensity values up to a threshold intensity value and (ii) gain values based on one or more input parameters for intensity values above the threshold intensity value. In addition, the method includes combining the intensity-gain curves to generate a 3D lookup table, which identifies the gain values for the anchor points in the image at each of multiple intensity values.
-
公开(公告)号:US20230252608A1
公开(公告)日:2023-08-10
申请号:US17666166
申请日:2022-02-07
Applicant: Samsung Electronics Co., Ltd.
Inventor: Yingmao Li , Hamid R. Sheikh , John Seokjun Lee , Youngmin Kim , Jun Ki Cho , Seung-Chul Jeon
IPC: G06T5/00
CPC classification number: G06T5/005 , G06T2207/20081 , G06T2207/10144 , G06T2207/20084
Abstract: A method includes obtaining, using a stationary sensor of an electronic device, multiple image frames including first and second image frames. The method also includes generating, using multiple previously generated motion vectors, a first motion-distorted image frame using the first image frame and a second motion-distorted image frame using the second image frame. The method further includes adding noise to the motion-distorted image frames to generate first and second noisy motion-distorted image frames. The method also includes performing (i) a first multi-frame processing (MFP) operation to generate a ground truth image using the motion-distorted image frames and (ii) a second MFP operation to generate an input image using the noisy motion-distorted image frames. In addition, the method includes storing the ground truth and input images as an image pair for training an artificial intelligence/machine learning (AI/ML)-based image processing operation for removing image distortions caused by handheld image capture.
-
公开(公告)号:US20230245494A1
公开(公告)日:2023-08-03
申请号:US17591530
申请日:2022-02-02
Applicant: Samsung Electronics Co., Ltd.
Inventor: Zeeshan Nadir , John W. Glotzbach , Hamid R. Sheikh
CPC classification number: G06V40/161 , G06T7/10 , G06T5/008 , G06T2207/20084 , G06T2207/20081 , G06T2207/30201
Abstract: An apparatus includes a memory configured to store images and a processor. The processor is configured to receive an input image. The processor is further configured to partition a human mask in the input image using a segmentation algorithm. The processor is also configured to generate a skin map based on identifying skin in the input image using the human mask. In addition, the processor is configured to process an output image with brightening applied using the skin map.
-
-
-
-
-
-
-
-
-