中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

109 records (took 0.031 seconds)

    Machine learning-based approaches for synthetic training data generation and image sharpening
    42.
    发明授权
    Machine learning-based approaches for synthetic training data generation and image sharpening 有权

    公开(公告)号：US12272032B2

    公开(公告)日：2025-04-08

    申请号：US17820795

    申请日：2022-08-18

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Devendra K. Jangid ,  John Seokjun Lee ,  Hamid R. Sheikh

    IPC: G06T5/70

    Abstract: A method includes obtaining an input image that contains blur. The method also includes providing the input image to a trained machine learning model, where the trained machine learning model includes (i) a shallow feature extractor configured to extract one or more feature maps from the input image and (ii) a deep feature extractor configured to extract deep features from the one or more feature maps. The method further includes using the trained machine learning model to generate a sharpened output image. The trained machine learning model is trained using ground truth training images and input training images, where the input training images include versions of the ground truth training images with blur created using demosaic and noise filtering operations.

    MOTION-AWARE NEURAL RADIANCE FIELD NETWORK TRAINING
    44.
    发明申请
    MOTION-AWARE NEURAL RADIANCE FIELD NETWORK TRAINING 有权

    公开(公告)号：US20240420341A1

    公开(公告)日：2024-12-19

    申请号：US18334931

    申请日：2023-06-14

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Yahang Li ,  Nguyen Thang Long Le ,  Hamid R. Sheikh

    IPC: G06T7/246 ,  G06T7/11 ,  G06T7/90 ,  G06T17/00 ,  G06V10/44

    Abstract: A method includes obtaining multiple training image frames of a scene, where the training image frames are captured at multiple viewpoints and multiple viewing angles relative to the scene. The method also includes generating multiple initial motion maps using the training image frames and identifying three-dimensional (3D) feature points associated with the scene using the training image frames. The method further includes generating tuned motion masks using the initial motion maps and projections of the 3D feature points onto the initial motion maps. In addition, the method includes training a machine learning model using the training image frames and the tuned motion masks, where the machine learning model is trained to generate 3D information about the scene from viewpoints and viewing angles not captured in the training image frames.

    System and method for multi-exposure, multi-frame blending of red-green-blue-white (RGBW) images
    45.
    发明授权
    System and method for multi-exposure, multi-frame blending of red-green-blue-white (RGBW) images 有权

    公开(公告)号：US12094086B2

    公开(公告)日：2024-09-17

    申请号：US17587309

    申请日：2022-01-28

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Long N. Le ,  Hamid R. Sheikh ,  John W. Glotzbach

    IPC: G06T5/50 ,  G06T5/73

    CPC classification number: G06T5/50 ,  G06T5/73 ,  G06T2207/10024 ,  G06T2207/20221

    Abstract: A method includes obtaining multiple images of a scene using at least one red-green-blue-white (RGBW) image sensor. The method also includes generating multi-channel frames at different exposure levels from the images. The method further includes estimating motion across exposure differences between the different exposure levels using a white channel of the multi-channel frames as a guidance signal to generate multiple motion maps. The method also includes estimating saturation across the exposure differences between the different exposure levels to generate multiple saturation maps. The method further includes using the generated motion maps and saturation maps to recover saturations from the different exposure levels and generate a saturation-free RGBW frame. In addition, the method includes processing the saturation-free RGBW frame to generate a final image of the scene.

    System and method for motion warping using multi-exposure frames
    47.
    发明授权
    System and method for motion warping using multi-exposure frames 有权

    公开(公告)号：US11503221B2

    公开(公告)日：2022-11-15

    申请号：US16837785

    申请日：2020-04-01

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Anqi Yang ,  John W. Glotzbach ,  Hamid R. Sheikh

    IPC: H04N5/235 ,  H04N19/42 ,  G06T5/00 ,  G06T5/50

    Abstract: A method includes obtaining, using at least one image sensor of an electronic device, a first image frame and multiple second image frames of a scene. Each of the second image frames has an exposure time different from an exposure time of the first image frame. The method also includes encoding, using at least one processor, each of the first image frame and the second image frames using a convolutional neural network to generate a corresponding feature map. The method further includes aligning, using the at least one processor, encoded features of the feature map corresponding to the first image frame with encoded features of the feature maps corresponding to the second image frames.

    PIXEL BLENDING FOR SYNTHESIZING VIDEO FRAMES WITH OCCLUSION AND WATERMARK HANDLING
    49.
    发明申请
    PIXEL BLENDING FOR SYNTHESIZING VIDEO FRAMES WITH OCCLUSION AND WATERMARK HANDLING 有权

    公开(公告)号：US20220303495A1

    公开(公告)日：2022-09-22

    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 ,  G06T3/00 ,  G06T1/00 ,  H04N1/32

    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.

Patent Agency Ranking