-
公开(公告)号:US20240394923A1
公开(公告)日:2024-11-28
申请号:US18201386
申请日:2023-05-24
Applicant: GoPro, Inc.
Inventor: Stephane Valente , Miguel Marques , Romain Gounelle
Abstract: Multiple images that include a first image, a second image, and a third image are received. The multiple images are such that the second image is temporally between the first image and the third image. The first image, the second image, and the third image are combined to obtain a long-exposure image. High dynamic range processing is applied to the second image and the long-exposure image to obtain an output image with a larger dynamic range than a dynamic range of the second image. The high dynamic range processing uses the second image as a short-exposure image. An image based on the output image is transmitted, stored, or displayed.
-
公开(公告)号:US11979668B2
公开(公告)日:2024-05-07
申请号:US17299470
申请日:2019-10-17
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guérin , Julien Caron , Miguel Marques
CPC classification number: H04N23/81 , G06T5/50 , G06T5/70 , G06T5/92 , G06T7/90 , H04N23/741 , G06T2207/20208 , G06T2207/20221
Abstract: Systems and methods are disclosed for high dynamic range anti-ghosting and fusion. For example, methods may include receiving images from image sensors in a linear domain, each image having different exposures or gains, blending luminance values at each pixel from each of the images to generate a blended image, selecting an useful image based on degree of useful information for a pixel, calculating a distance value from the images for the pixel, locating from a look-up table (LUT) an anti-ghosting weight using the useful image and the distance value for the pixel, proportionally applying the located anti-ghosting weight to the pixel for each of the input images to generate an output image, all being performed in the linear domain, and storing, displaying, or transmitting the output image based on at least the anti-ghosting weight.
-
公开(公告)号:US20220030152A1
公开(公告)日:2022-01-27
申请号:US17299470
申请日:2019-10-17
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guérin , Julien Caron , Miguel Marques
Abstract: Systems and methods are disclosed for high dynamic range anti-ghosting and fusion. For example, methods may include receiving images from image sensors in a linear domain, each image having different exposures or gains, blending luminance values at each pixel from each of the images to generate a blended image, selecting an useful image based on degree of useful information for a pixel, calculating a distance value from the images for the pixel, locating from a look-up table (LUT) an anti-ghosting weight using the useful image and the distance value for the pixel, proportionally applying the located anti-ghosting weight to the pixel for each of the input images to generate an output image, all being performed in the linear domain, and storing, displaying, or transmitting the output image based on at least the anti-ghosting weight.
-
公开(公告)号:US20190095713A1
公开(公告)日:2019-03-28
申请号:US16142608
申请日:2018-09-26
Applicant: GoPro, Inc.
Inventor: Sylvain Leroy , Adrien Cariou , Miguel Marques , Julien Caron , Bruno Faure , Stéphane Belardi
Abstract: Image analysis includes obtaining, from an image signal processor, image processing information corresponding to a previously processed image, obtaining scene classification information for an input image based on the image processing information, generating a processed image by processing the input image based on the scene classification information, and outputting the processed image. The image processing information includes automatic white balance correction information and obtaining the scene classification information includes obtaining the scene classification information based on the automatic white balance correction information.
-
公开(公告)号:US11238285B2
公开(公告)日:2022-02-01
申请号:US17222538
申请日:2021-04-05
Applicant: GoPro, Inc.
Inventor: Sylvain Leroy , Adrien Cariou , Miguel Marques , Julien Caron , Bruno Faure , Stéphane Belardi
Abstract: Image analysis includes obtaining, from an image signal processor, image processing information corresponding to a previously processed image, obtaining scene classification information for an input image based on the image processing information, generating a processed image by processing the input image based on the scene classification information, and outputting the processed image. The image processing information includes automatic white balance correction information and obtaining the scene classification information includes obtaining the scene classification information based on the automatic white balance correction information.
-
公开(公告)号:US20210224543A1
公开(公告)日:2021-07-22
申请号:US17222538
申请日:2021-04-05
Applicant: GoPro, Inc.
Inventor: Sylvain Leroy , Adrien Cariou , Miguel Marques , Julien Caron , Bruno Faure , Stéphane Belardi
Abstract: Image analysis includes obtaining, from an image signal processor, image processing information corresponding to a previously processed image, obtaining scene classification information for an input image based on the image processing information, generating a processed image by processing the input image based on the scene classification information, and outputting the processed image. The image processing information includes automatic white balance correction information and obtaining the scene classification information includes obtaining the scene classification information based on the automatic white balance correction information.
-
公开(公告)号:US10970552B2
公开(公告)日:2021-04-06
申请号:US16142608
申请日:2018-09-26
Applicant: GoPro, Inc.
Inventor: Sylvain Leroy , Adrien Cariou , Miguel Marques , Julien Caron , Bruno Faure , Stéphane Belardi
Abstract: Image analysis includes obtaining, from an image signal processor, image processing information corresponding to a previously processed image, obtaining scene classification information for an input image based on the image processing information, generating a processed image by processing the input image based on the scene classification information, and outputting the processed image. The image processing information includes automatic white balance correction information and obtaining the scene classification information includes obtaining the scene classification information based on the automatic white balance correction information.
-
-
-
-
-
-