-
公开(公告)号：US10719927B2
公开(公告)日：2020-07-21
申请号：US15862492
申请日：2018-01-04
Applicant: Samsung Electronics Co., Ltd.
Inventor： Raja Bala , Hamid R. Sheikh , John Glotzbach
Abstract: An electronic device, method, and computer readable medium for multi-frame image processing using semantic saliency are provided. The electronic device includes a camera, a display, and a processor. The processor is coupled to the camera and the display. The processor receives a plurality of frames captured by the camera during a capture event; identifies a salient region in each of the plurality of frames; determines a reference frame from the plurality of frames based on the identified salient regions; fuses non-reference frames with the determined reference frame into a completed image output.
-
公开(公告)号：US12254601B2
公开(公告)日：2025-03-18
申请号：US17586435
申请日：2022-01-27
Applicant: Samsung Electronics Co., Ltd.
Inventor： Long N. Le , Yibo Xu , John W. Glotzbach , Zhen Tong , Hamid R. Sheikh
IPC: G06T5/70 , G06T5/10 , H04N25/683
Abstract: A method includes obtaining a blended red-green-blue (RGB) image frame of a scene. The method also includes performing, using at least one processing device of an electronic device, an interband denoising operation to remove at least one of noise and one or more artifacts from the blended RGB image frame in order to produce a denoised RGB image frame. Performing the interband denoising operation includes performing filtering of red, green, and blue color channels of the blended RGB image frame to remove at least one of the noise and the one or more artifacts from the blended RGB image frame. The filtering of the red and blue color channels of the blended RGB image frame is based on image data of at least one of the green color channel and a white color channel of the blended RGB image frame.
-
63.发明授权公开(公告)号：US12238424B2
公开(公告)日：2025-02-25
申请号：US18474783
申请日：2023-09-26
Applicant: Samsung Electronics Co., Ltd.
Inventor： Ibrahim Pekkucuksen , Hamid R. Sheikh
Abstract: A method includes obtaining, using at least one processing device of an electronic device, multiple image frames having different exposure levels. The method also includes determining whether a moving saturated region is present in at least some of the image frames. The method further includes selecting one of the image frames as a reference frame, where the selected image frame depends on whether the moving saturated region is present in at least some of the image frames. The selected image frame may have a first exposure level when the moving saturated region is present in at least some of the image frames, and the selected image frame may have a second exposure level longer than the first exposure level when the moving saturated region is not present in the image frames.
-
公开(公告)号：US20250037237A1
公开(公告)日：2025-01-30
申请号：US18360536
申请日：2023-07-27
Applicant: Samsung Electronics Co., Ltd.
Inventor： Devendra Kumar Jangid , Abhiram Gnanasambandam , John W. Glotzbach , John Seokjun Lee , Hamid R. Sheikh
Abstract: A method includes extracting multiple shallow features from a low-resolution image using a shallow feature extractor that includes a quaternion convolutional network. The method also includes extracting multiple deep features from the multiple shallow features using a deep feature extractor that includes multiple quaternion residual distillation blocks (QRDBs), where each QRDB includes a quaternion self-attention module. The method further includes reconstructing the multiple deep features into a high-resolution image. Each QRDB may further include a quaternion gated deconvolutional feed forward network (QGDFN) configured to suppress one or more of the multiple deep features.
-
65.发明申请公开(公告)号：US20250022098A1
公开(公告)日：2025-01-16
申请号：US18350558
申请日：2023-07-11
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yahang Li , Nguyen Thang Long Le , Hamid R. Sheikh
Abstract: A method includes obtaining, using at least one processing device of an electronic device, raw image frames of a scene. The raw image frames include different sets of raw image frames captured at different viewpoints and different viewing angles relative to the scene. The method also includes performing, using the at least one processing device, blending of each set of raw image frames in order to generate blended image frames of the scene. The method further includes training, using the at least one processing device, a machine learning model using the blended image frames. The machine learning model is trained to generate three-dimensional (3D) information about the scene from viewpoints and viewing angles not captured in the sets of raw image frames.
-
Patent Agency Ranking
公开(公告)号：US12148124B2
公开(公告)日：2024-11-19
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：US12141894B2
公开(公告)日：2024-11-12
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 , G06T7/55 , G06V10/60 , G06V10/774 , G06V10/776 , H04N23/45
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.
-
公开(公告)号：US12079971B2
公开(公告)日：2024-09-03
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
CPC classification number: G06T5/77 , G06T2207/10144 , G06T2207/20081 , 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.
-
69.发明授权公开(公告)号：US12022204B2
公开(公告)日：2024-06-25
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.
-
公开(公告)号：US20240202874A1
公开(公告)日：2024-06-20
申请号：US18068916
申请日：2022-12-20
Applicant: Samsung Electronics Co., Ltd.
Inventor： Madhuri Suthar , Tyler Luu , Nguyen Thang Long Le , John W. Glotzbach , Hamid R. Sheikh
CPC classification number: G06T5/30 , G06T3/4015 , G06T5/50 , G06T2207/20024 , G06T2207/20036 , G06T2207/20212
Abstract: A method includes obtaining input image frames, including at least two captured using different capture conditions. The method also includes separating color channels of each image frame and generating at least one bad pixel map for each color channel of each image frame. Each bad pixel map is generated by identifying one or more outliers in pixel values in the color channel based on an intensity distribution of pixel values in an operation window within the color channel. The operation window has a window size based on the capture condition and/or local image content in the corresponding image frame. The method further includes combining the bad pixel maps and performing a morphological operation to refine the combined bad pixel map. In addition, the method includes using one or more coordinates of one or more bad pixels in the refined bad pixel map to update one or more pixel values of at least one image frame.
-
-
-
-
-
-
-
-
-
Search Results
109
records
(took 0.032 seconds)
