METHOD AND APPARATUS WITH UPDATING OF ALGORITHM FOR GENERATING DISPARITY IMAGE

    公开(公告)号:US20210144355A1

    公开(公告)日:2021-05-13

    申请号:US16837320

    申请日:2020-04-01

    Abstract: A method with algorithm updating includes: receiving a first input batch including one or more first images; generating a first output batch with respect to the first input batch using an algorithm configured to generate a disparity image, the first output batch including one or more first output images; receiving a second input batch corresponding to the first input batch, the second input batch including one or more second images having viewpoints that are different from viewpoints of the one or more first images; generating a test batch based on the first output batch and the second input batch, the test batch including one or more test images; and updating the algorithm based on a difference between the first input batch and the test batch.

    METHOD AND APPARATUS WITH IMAGE DEPTH ESTIMATION

    公开(公告)号:US20220036573A1

    公开(公告)日:2022-02-03

    申请号:US17116063

    申请日:2020-12-09

    Abstract: A method and apparatus with image depth estimation are provided. The method includes obtaining a first statistical value associated with a depth for each of plural pixels included in an input image based on a first channel of output data obtained by applying the input image to a neural network, obtaining a second statistical value associated with a depth for each of the plural pixels in the input image based on a second channel of the output data, and estimating depth information of each of the plural pixels in the input image based on the first statistical value and the second statistical value. The neural network may be trained based on a probability distribution for a depth of each pixel in an image based on a first statistical value and a second statistical value that are obtained corresponding to an image with predetermined depth information in the training data.

    METHOD AND DEVICE WITH IMAGE PROCESSING
    7.
    发明公开

    公开(公告)号:US20240161238A1

    公开(公告)日:2024-05-16

    申请号:US18318475

    申请日:2023-05-16

    CPC classification number: G06T5/001 G06T5/50 G06T2207/20084

    Abstract: An electronic device, including one or more processors configured to execute instructions; and a memory storing the instructions which, when executed by the one or more processors, configures the one or more processors to generate high-quality feature data of a current frame, by implementing a feature restoration model that is provided reference feature data, received by an electronic device, and corresponding to compressed feature data of a reference image corresponding to a first time that is different from a second time to which the current frame corresponds, and low-quality feature data received by the electronic device, and corresponding to compressed data of the current frame, that has a lower image quality than the reference image; and generate a current frame of a third image quality higher than the second image quality, based on the high-quality feature data

    APPARATUS AND METHOD WITH VIDEO PROCESSING
    8.
    发明公开

    公开(公告)号:US20240089486A1

    公开(公告)日:2024-03-14

    申请号:US18093377

    申请日:2023-01-05

    CPC classification number: H04N19/513 H04N19/105 H04N19/137 H04N19/172

    Abstract: Disclosed are an apparatus and method with video processing. A computing apparatus includes one or more processors and storage storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: generate cluster maps using clusters generated by performing clustering, wherein the generating the cluster maps performed based on a reference frame of a video generated based on a previous point in time of the video, generate a predicted frame by performing motion compensation based on the cluster maps, and generate a decoded frame by performing decoding based on the current frame and the predicted frame.

Patent Agency Ranking