-
公开(公告)号:US20250005801A1
公开(公告)日:2025-01-02
申请号:US18884310
申请日:2024-09-13
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Hu CHEN , Zehui LIN , Quanhe YU , Kangying CAI , Rong WEI
IPC: G06T9/00
Abstract: The technology of this application relates to a probe data processing method and a probe data encoding method, and an apparatus. The probe data processing method in this application includes obtaining a bitstream, parsing the bitstream to obtain first probe data in a current probe data group, where the first probe data corresponds to a non-linear domain signal, obtaining a conversion function parameter of the current probe data group, obtaining an inverse conversion function of the current probe data group based on the conversion function parameter of the current probe data group, and performing spatial inverse conversion on the first probe data according to the inverse conversion function to obtain second probe data in the current probe data group, where the second probe data corresponds to one or more probes in a three-dimensional scene, and the second probe data corresponds to a linear domain signal.
-
公开(公告)号:US20210174092A1
公开(公告)日:2021-06-10
申请号:US17174536
申请日:2021-02-12
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Zhijie ZHAO , Yuntan FANG , Jun ZHA , Hu CHEN , Jiantong ZHOU
Abstract: The invention relates to an image processing apparatus for extracting a feature from an image of a scene. The apparatus may comprises processing circuitry configured, in response to a feature extraction event, to extract a feature from first image data representing a first image of a scene, wherein the feature extraction event is based on second image data representing a second image of the scene. The image processing apparatus may include an event driven sensor and the second image may include may include a positive/negative amount of the intensity change and the location of the intensity change. Moreover, the invention relates to a corresponding image processing method.
-
公开(公告)号:US20240331117A1
公开(公告)日:2024-10-03
申请号:US18743607
申请日:2024-06-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Weiwei XU , Haitao YANG , Quanhe YU , Hu CHEN , Yichuan WANG
Abstract: A dynamic range mapping method and apparatus for a panoramic video that relate to the field of video image processing are provided. The method includes: splitting a two-dimensional panoramic projection image corresponding to any frame of three-dimensional panoramic image in a panoramic video, to obtain a plurality of regions of the two-dimensional panoramic projection image; obtaining metadata of the two-dimensional panoramic projection image, where the metadata includes metadata information elements separately corresponding to the plurality of regions, and a metadata information element corresponding to one region includes dynamic mapping information of the region; determining dynamic mapping information of each pixel in a current angle of view range based on respective dynamic mapping information of the plurality of regions; and performing dynamic range mapping on each pixel in the current angle of view range, to obtain a two-dimensional panoramic projection image that is used for display or subsequent processing.
-
公开(公告)号:US20210203997A1
公开(公告)日:2021-07-01
申请号:US17197500
申请日:2021-03-10
Applicant: Huawei Technologies Co., Ltd.
Inventor: Anton Igorevich VESELOV , Hu CHEN , Francesco ROMANO , Zhijie ZHAO , Marat Ravilevich GILMUTDINOV
IPC: H04N19/70 , H04N19/184 , G06K9/46
Abstract: The present disclosure relates to hybrid video and feature encoding and decoding, with the encoding and decoding of the image feature being performed independently or differentially. The video and feature are encoded and decoded in separate layers, e.g., base layer and enhancement layer. The feature is extracted for a frame of the video, providing a frame-based feature-video association. A feature is extracted from an uncompressed video encoded in an enhancement layer into a feature bitstream. The video is encoded into a video bitstream, with the feature bitstream being embedded into the video bitstream by multiplexing both streams into an output bitstream. The image feature, which may be a differential image feature, is included in a sequence enhancement information SEI message of a frame header information of the video. The output bitstream is provided as input bitstream to a decoder, which de-multiplexes the input bitstream into a video bitstream and feature bitstream, using the SEI message of the frame header. Both bitstreams are decoded in their respective layers, and the image feature is located in the video using the frame-based feature-video association.
-
公开(公告)号:US20250008105A1
公开(公告)日:2025-01-02
申请号:US18884281
申请日:2024-09-13
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Zehui LIN , Kangying CAI , Hu CHEN , Rong WEI
IPC: H04N19/126 , H04N19/159
Abstract: Embodiments of the present disclosure relate to the field of media technologies, and disclose an encoding method and apparatus, and a decoding method and apparatus, to reduce a rendering loss caused by compression of probe data. The encoding method includes: first determining a target normalization combination of a probe data group, then normalizing the probe data group based on the target normalization combination to obtain a normalized probe data group, and encoding the normalized probe data group into a bitstream. The target normalization combination minimizes a rendering loss corresponding to the probe data group among a plurality of normalization combinations, and the target normalization combination includes a target normalization method and a target normalization parameter.
-
公开(公告)号:US20240054623A1
公开(公告)日:2024-02-15
申请号:US18494247
申请日:2023-10-25
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Hu CHEN , Quanhe YU , Weiwei XU , Jiantong ZHOU , Ruihua LI
CPC classification number: G06T5/009 , G06T5/40 , G06T7/50 , G06T2207/10012 , G06T2207/10024 , G06T2207/20208
Abstract: This application relates to the field of image processing technologies, and discloses an image processing method and system, and a device, to resolve a problem that tone mapping greatly affects perception of a binocular 3D image. Based on a disparity map of a binocular image, a tone mapping curve is determined for a display device to display an image, instead of being generated merely based on image content. This makes a contrast of a tone mapped binocular image reach at least a level before tone mapping, thereby meeting a minimum disparity variation requirement for 3D perception by human eyes, and improving 3D perception of a 3D image displayed by the display device.
-
公开(公告)号:US20230054046A1
公开(公告)日:2023-02-23
申请号:US17975893
申请日:2022-10-28
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Weiwei XU , Quanhe YU , Hu CHEN , Yichuan WANG
Abstract: This application provides a dynamic range mapping method and apparatus. The dynamic range mapping method includes: obtaining a display parameter of a terminal device; obtaining feature information of image data; obtaining a first parameter of a first tone mapping curve of the image data; when a preset condition is met, obtaining a second parameter of a second tone mapping curve based on the first parameter, the display parameter of the terminal device, and the feature information of the image data, where output luminance at a first point on the second tone mapping curve is not greater than input luminance at the first point on the second tone mapping curve; and performing dynamic range mapping on the image data based on the second parameter of the second tone mapping curve.
-
公开(公告)号:US20220239880A1
公开(公告)日:2022-07-28
申请号:US17659253
申请日:2022-04-14
Applicant: Huawei Technologies Co., Ltd.
Inventor: Weiwei XU , Quanhe YU , Hu CHEN , Xiaodong XU
Abstract: A chrominance adjustment method and apparatus, and a storage medium are provided. The method includes: determining a color adjustment coefficient of a chrominance component of a color signal based on a reference display device maximum luminance value (RML) and/or a source maximum luminance value (SML); and adjusting the chrominance component of the color signal based on the color adjustment coefficient.
-
公开(公告)号:US20240221136A1
公开(公告)日:2024-07-04
申请号:US18604784
申请日:2024-03-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Weiwei XU , Jinsong WEN , Lei WU , Zhongke MA , Yanbing JIA , Quanhe YU , Zizhong WANG , Yichuan WANG , Hu CHEN
CPC classification number: G06T5/92 , G06T7/11 , G06T2207/10016 , G06T2207/10024 , G06T2207/20208
Abstract: This application provides a tone mapping method including: obtaining a to-be-displayed image frame and metadata which includes at least one metadata information unit; segmenting the to-be-displayed image frame into a plurality of segmentation regions in a target segmentation manner, and determining a correspondence between the plurality of segmentation regions and the at least one metadata information unit; and for an ith pixel: determining, for a plurality of pixels included in a preset region, at least one related segmentation region to which the plurality of pixels belong, and determining a related metadata information unit corresponding to each related segmentation region; obtaining a tone mapping subvalue corresponding to the related segmentation region, and allocating a corresponding weighting factor to the related segmentation region; obtaining a tone mapping value based on the tone mapping subvalue and the weighting factor; and performing tone mapping based on the tone mapping value.
-
公开(公告)号:US20240153051A1
公开(公告)日:2024-05-09
申请号:US18411529
申请日:2024-01-12
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Weiwei XU , Quanhe YU , Hu CHEN , Yichuan WANG
CPC classification number: G06T5/92 , G06T3/16 , G06T5/50 , G06T7/11 , G06T2207/10016 , G06T2207/20208
Abstract: This application provides a tone mapping method and apparatus for a panoramic image. The tone mapping method includes: determining one or more target metadata information units of a first pixel from a plurality of metadata information units, where the plurality of metadata information units are obtained by parsing a bitstream, the first pixel is any pixel in a to-be-processed panoramic video two-dimensional planar projection, the plurality of metadata information units correspond to a plurality of segmented regions included in a panoramic video three-dimensional spherical representation panoramic image, and there is a mapping relationship between the panoramic video two-dimensional planar projection and the panoramic video three-dimensional spherical representation panoramic image; and performing tone mapping on a pixel value of the first pixel based on the one or more target metadata information units, to obtain a target tone mapping value of the first pixel.
-
-
-
-
-
-
-
-
-