-
公开(公告)号:US11616960B2
公开(公告)日:2023-03-28
申请号:US17210478
申请日:2021-03-23
申请人: Apple Inc.
发明人: Jim C. Chou , Alexandros Tourapis
IPC分类号: H04N19/159 , H04N19/154 , H04N19/59 , H04N19/86 , H04N19/46 , G06T9/00 , G06N3/04 , G06N3/08 , H04N19/102 , H04N19/117 , H04N19/189 , H04N19/132 , H04N19/90 , H04N19/136 , H04N19/172 , H04N19/436
摘要: System and method for improving video encoding and/or video decoding. In embodiments, a video encoding pipeline includes a main encoding pipeline that compresses source image data corresponding with an image frame by processing the source image data based at least in part on encoding parameters to generate encoded image data. Additionally the video encoding pipeline includes a machine learning block communicatively coupled to the main encoding pipeline, in which the machine learning block analyzes content of the image frame by processing the source image data based at least in part on machine learning parameters implemented in the machine learning block when the machine learning block is enabled by the encoding parameters; and the video encoding pipeline adaptively adjusts the encoding parameters based at least in part on the content expected to be present in the image frame to facilitate improving encoding efficiency.
-
公开(公告)号:US20220408109A1
公开(公告)日:2022-12-22
申请号:US17896350
申请日:2022-08-26
申请人: VID SCALE, INC.
IPC分类号: H04N19/52 , H04N19/176 , H04N19/119 , H04N19/46 , H04N19/593 , H04N19/11 , H04N19/124 , H04N19/14 , H04N19/80 , H04N19/90 , H04N19/60 , H04N19/59 , H04N19/182
摘要: Systems, methods, and instrumentalities are disclosed relating to intra prediction of a video signal based on mode-dependent subsampling. A block of coefficients associated with a first sub block of a video block, one or more blocks of coefficients associated with one or more remaining sub blocks of the video block, and an indication of a prediction mode for the video block may be received. One or more interpolating techniques, a predicted first sub block, and the predicted sub blocks of the one or more remaining sub blocks may be determined. A reconstructed first sub block and one or more reconstructed remaining sub blocks may be generated. A reconstructed video block may be formed based on the prediction mode, the reconstructed first sub block, and the one or more reconstructed remaining sub blocks.
-
公开(公告)号:US11533514B2
公开(公告)日:2022-12-20
申请号:US16911775
申请日:2020-06-25
发明人: Chi Wang , Pongsak Lasang , Toshiyasu Sugio , Tatsuya Koyama
摘要: An encoding method according to the present disclosure includes: inputting three-dimensional data including three-dimensional coordinate data to a deep neural network (DNN); encoding the three-dimensional data by the DNN to generate encoded three-dimensional data; and outputting the encoded three-dimensional data.
-
公开(公告)号:US20220256076A1
公开(公告)日:2022-08-11
申请号:US17543629
申请日:2021-12-06
申请人: GoPro, Inc.
发明人: Bruno César Douady , Michael Serge Andre Kraak , Guillaume Matthieu Guérin , Thomas Nicolas Emmanuel Veit
IPC分类号: H04N5/232 , H04N5/247 , H04N17/00 , G06T7/80 , G06T3/40 , H04N19/10 , H04N19/136 , H04N19/176 , H04N19/423 , H04N19/70 , H04N19/90 , H04N13/271 , G06T5/20 , G06T5/50 , H04N5/357 , H04N19/85 , G06T3/00 , H04N5/225
摘要: Systems and methods are disclosed for image signal processing. For example, methods may include receiving a current image of a sequence of images from an image sensor; combining the current image with a recirculated image to obtain a noise reduced image, where the recirculated image is based on one or more previous images of the sequence of images from the image sensor; determining a noise map for the noise reduced image, where the noise map is determined based on estimates of noise levels for pixels in the current image, a noise map for the recirculated image, and a set of mixing weights; recirculating the noise map with the noise reduced image to combine the noise reduced image with a next image of the sequence of images from the image sensor; and storing, displaying, or transmitting an output image that is based on the noise reduced image.
-
公开(公告)号:US20220215593A1
公开(公告)日:2022-07-07
申请号:US17566282
申请日:2021-12-30
摘要: An example device for filtering decoded video data includes one or more processors configured to execute a neural network filtering unit to: receive data from one or more other units of the device, the data from the one or more other units of the device being different than data for a decoded picture of video data, and wherein to receive the data from the one or more other units of the device, the one or more processors are configured to execute the neural network filtering unit to receive boundary strength data from a deblocking unit of the device; determine one or more neural network models to be used to filter a portion of the decoded picture; and filter the portion of the decoded picture using the one or more neural network models and the data from the one or more other units of the device, including the boundary strength data.
-
公开(公告)号:US11089338B2
公开(公告)日:2021-08-10
申请号:US16584376
申请日:2019-09-26
申请人: Vital Images, Inc.
发明人: William D. Hachfeld
IPC分类号: G06K9/00 , H04N19/93 , H04N19/172 , H04N19/91 , H04N19/184 , H04N19/593 , H04N19/80 , H04N19/176 , G16H30/20 , H04N19/90 , H04N19/59 , G16H30/00
摘要: Techniques and configurations for compression of image data in a progressive, lossless manner are disclosed. In an example, three-dimensional medical images may be compressed and decompressed with high-speed operations, through a compression technique performed on a cube (chunk) of voxels that includes generating a subsampled or filtered cube of voxels, and generating and optimizing a delta data set between the cube of voxels and the subsampled cube of voxels. This optimized delta data set is operable with a decompression technique to losslessly recreate the cube of voxels. Further, the compression technique may be progressively performed with multiple iterations, to allow multiple lower resolution versions of the images prior to loading or receiving the entire compressed data that is reconstructable in a lossless form. Use of this technique may result in dramatically reduced time to first image when visualizing 3D images and performing image data transfers.
-
公开(公告)号:US11057547B2
公开(公告)日:2021-07-06
申请号:US16733927
申请日:2020-01-03
申请人: SONY CORPORATION
发明人: Ikuo Tsukagoshi
IPC分类号: H04N5/202 , H04N5/225 , H04N19/90 , H04N21/235 , H04N19/70 , H04N21/2343 , H04N21/485
摘要: To enable a receiving side to appropriately perform processing of obtaining display image data from transmission video data having a predetermined photoelectric conversion characteristic. Input video data is processing and transmission video data having a predetermined photoelectric conversion characteristic is obtained. Encoding processing is applied to the transmission video data and a video stream is obtained. A container of a predetermined format, including the video stream, is transmitted. Information indicating a photoelectric conversion of the input video data is inserted into the video stream and/or the container.
-
公开(公告)号:US20210185361A1
公开(公告)日:2021-06-17
申请号:US17188473
申请日:2021-03-01
申请人: Apple Inc.
发明人: Xiaohua YANG , Alexandros TOURAPIS , Dazhong ZHANG , Hang YUAN , Hsi-Jung WU , Jae Hoon KIM , Jiefu ZHAI , Ming CHEN , Xiaosong ZHOU
IPC分类号: H04N19/90 , H04N19/52 , H04N19/597 , G06F3/01 , H04N21/2343
摘要: In communication applications, aggregate source image data at a transmitter exceeds the data that is needed to display a rendering of a viewport at a receiver. Improved streaming techniques that include estimating a location of a viewport at a future time. According to such techniques, the viewport may represent a portion of an image from a multi-directional video to be displayed at the future time, and tile(s) of the image may be identified in which the viewport is estimated to be located. In these techniques, the image data of tile(s) in which the viewport is estimated to be located may be requested at a first service tier, and the other tile in which the viewport is not estimated to be located may be requested at a second service tier, lower than the first service tier.
-
公开(公告)号:US11019366B2
公开(公告)日:2021-05-25
申请号:US16413992
申请日:2019-05-16
申请人: GOOGLE LLC
IPC分类号: G06T9/00 , H04N19/90 , H04N19/186 , H04N19/176
摘要: An encoder system can include a pixel grid generator to receive an image having a first dimension, generate a grid having a second dimension, add a plurality of points to positions on the grid, and map a plurality of pixels of the image to the plurality of points. The encoder system can include a color module to assign a color to each of the plurality of points using a color table, a triangulation module to generate a plurality of vertices based on the plurality of points and triangulate the grid using the vertices, and a compression module to compress the vertices as a set of compressed vertex positions and a set of vertex colors.
-
公开(公告)号:US10986280B2
公开(公告)日:2021-04-20
申请号:US16228970
申请日:2018-12-21
摘要: An electronic apparatus includes: a connecting unit (connector) that connects with an external apparatus; a setting unit sets a connection mode to any of a plurality of connection modes, including a first connection mode in which an image having a gradation resolution which is not higher than a first gradation resolution is outputted, and a second connection mode in which an image having a gradation resolution which is higher than the first gradation resolution is outputted; and a control unit controls so that in a case where the connection is in the second connection mode and an instruction to switch a first screen including a captured image to a second screen not including a captured image is received, the set connection mode is switched from the second connection mode to the first connection mode, and the second screen is outputted from the connecting unit.
-
-
-
-
-
-
-
-
-