公开(公告)号：US20190132591A1

公开(公告)日：2019-05-02

申请号：US15794938

申请日：2017-10-26

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Bin Zhu ,  Sang-Hee Lee ,  Qing Li

IPC: H04N19/124 ,  H04N19/167 ,  H04N19/59 ,  H04N19/184 ,  G06N3/10 ,  G06N3/04

Abstract: Techniques related to quantization parameter estimation for video coding are discussed. Such techniques may include generating features using a picture of input video received for encoding and applying a neural network to a feature vector including the features, a target bitrate, and a resolution of the picture to generate an estimated quantization parameter for encoding the picture.

公开(公告)号：US20180048901A1

公开(公告)日：2018-02-15

申请号：US15232613

申请日：2016-08-09

Applicant: INTEL CORPORATION

Inventor： Ximin Zhang ,  Sang-Hee Lee

IPC: H04N19/186 ,  H04N19/172 ,  H04L12/26 ,  H04N19/13 ,  H04N19/174 ,  H04N19/124 ,  H04N19/31

CPC classification number: H04N19/186 ,  H04L43/16 ,  H04N19/124 ,  H04N19/13 ,  H04N19/137 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176 ,  H04N19/31

Abstract: Techniques related to determining chroma quantization parameters for video coding are discussed. Such techniques may include generating first and second chroma quantization parameter offsets for first and second picture of a video sequence having a hierarchical coding structure such that the second chroma quantization parameter offset is greater than or equal to the first chroma quantization parameter offset in response to the first picture having a higher quality priority than the second picture.

公开(公告)号：US12184855B2

公开(公告)日：2024-12-31

申请号：US16953098

申请日：2020-11-19

Applicant: Intel Corporation

Inventor： Zhijun Lei ,  Ximin Zhang ,  Sang-hee Lee

IPC: H04N11/02 ,  H04N19/124 ,  H04N19/176 ,  H04N19/18 ,  H04N19/61

Abstract: Techniques related to video coding include content adaptive quantization that provides a selection between objective quality and subjective quality delta QP offsets.

公开(公告)号：US12108185B2

公开(公告)日：2024-10-01

申请号：US17461279

申请日：2021-08-30

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Abhishek R. Appu ,  Stanley J. Baran ,  Sang-Hee Lee ,  Atthar H. Mohammed ,  Jong Dae Oh ,  Hiu-Fai R. Chan ,  Ximin Zhang

IPC: H04N5/52 ,  G06T3/00 ,  G06T3/08 ,  H04N13/139 ,  H04N19/124 ,  H04N19/154 ,  H04N19/167 ,  H04N19/176 ,  H04N19/436 ,  H04N19/597 ,  H04N19/86 ,  H04N5/14 ,  H04N23/698

CPC classification number: H04N5/52 ,  G06T3/00 ,  G06T3/08 ,  H04N13/139 ,  H04N19/124 ,  H04N19/154 ,  H04N19/167 ,  H04N19/176 ,  H04N19/436 ,  H04N19/597 ,  H04N19/86 ,  G06T2207/10016 ,  H04N5/144 ,  H04N23/698

Abstract: An embodiment may include a display processor, memory to store a 2D frame corresponding to a projection from a 360 video, and a quality selector to select a quality factor for a block of the 2D frame based on quality information from neighboring blocks of the 2D frame, including blocks which are neighboring only in the 360 video space. The system may also include a range adjuster to adjust a search range for the 2D frame based on a search area of the 2D frame, a viewport manager to determine if a request for a viewport of the 2D frame extends beyond a first edge of the 2D frame and to fill the requested viewport with wrap-around image information, and/or a motion estimator to estimate motion information based on both color information and depth information. Other embodiments are disclosed and claimed.

公开(公告)号：US12022096B2

公开(公告)日：2024-06-25

申请号：US16869053

申请日：2020-05-07

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Sang-Hee Lee ,  Keith Rowe

IPC: H04N19/196 ,  H04N19/124 ,  H04N19/14 ,  H04N19/176 ,  H04N19/177

CPC classification number: H04N19/196 ,  H04N19/124 ,  H04N19/14 ,  H04N19/176 ,  H04N19/177

Abstract: An example apparatus for encoding video frames includes a mask selector to select a subset of visual masks according to an actual target compression ratio and GOP configuration and a complexity estimator to estimate a picture level spatial/temporal complexity for a current frame. The example apparatus further includes a GOP adaptive visual mask selector to specify a visual mask from the subset of the visual masks corresponding to the estimated spatial and temporal complexity value a good enough picture QP deriver to derive a good enough picture QP value using the visual mask. The example apparatus also includes an adjustor to adjust the good enough picture QP value based on block level human visual system sensitivity and statistics of already encoded frames to obtain a final human visual system QP map.

公开(公告)号：US11889096B2

公开(公告)日：2024-01-30

申请号：US16914083

申请日：2020-06-26

Applicant: INTEL CORPORATION

Inventor： Chen Wang ,  Ximin Zhang ,  Huan Dou ,  Yi-Jen Chiu ,  Sang-Hee Lee

IPC: G06T9/00 ,  G06T3/40 ,  H04N19/44 ,  H04N19/30 ,  G06N3/08 ,  H04N19/159 ,  H04N19/184 ,  H04N19/176 ,  H04N19/132 ,  G06F18/25 ,  G06V10/82

CPC classification number: H04N19/44 ,  G06F18/251 ,  G06N3/08 ,  G06T3/4007 ,  G06T3/4053 ,  G06T9/002 ,  G06V10/82 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/184 ,  H04N19/30

Abstract: Techniques related to accelerated video enhancement using deep learning selectively applied based on video codec information are discussed. Such techniques include applying a deep learning video enhancement network selectively to decoded non-skip blocks that are in low quantization parameter frames, bypassing the deep learning network for decoded skip blocks in low quantization parameter frames, and applying non-deep learning video enhancement to high quantization parameter frames.

公开(公告)号：US20230412808A1

公开(公告)日：2023-12-21

申请号：US18031563

申请日：2020-11-30

Applicant: Intel Corporation

Inventor： James Holland ,  Sang-hee Lee ,  Ximin Zhang ,  Zhan Lou

IPC: H04N19/126 ,  H04N19/149 ,  H04N19/172 ,  G06N20/00

CPC classification number: H04N19/126 ,  G06N20/00 ,  H04N19/172 ,  H04N19/149

Abstract: Techniques related to adaptive quantization matrix selection using machine learning for video coding are discussed. Such techniques include applying a machine learning model to generate an estimated quantization parameter for a frame and selecting a set of quantization matrices for encode of the frame from a number of sets of quantization matrices based on the estimated quantization parameter.

公开(公告)号：US11825088B2

公开(公告)日：2023-11-21

申请号：US16684952

申请日：2019-11-15

Applicant: INTEL CORPORATION

Inventor： Ximin Zhang ,  Sang-Hee Lee ,  Keith Rowe

IPC: H04N9/14 ,  H04N19/124 ,  H04N19/152 ,  H04N19/172 ,  H04N19/14

CPC classification number: H04N19/124 ,  H04N19/14 ,  H04N19/152 ,  H04N19/172

Abstract: An example apparatus for encoding video frames includes a frame analyzer to execute a look ahead analysis on a received set of frames. The frame analyzer includes a look ahead video analyzer to down-sample the set of frames and encode the down-sampled frames with a constant quantization parameter (QP). A number of generated bits for each of the frames is used as a complexity measurement for each of the frames. The apparatus further includes an encoder to encode the input frame using an adjusted bit allocation based on a relative complexity of the input frame in relation to a complexity of the set of frames.

公开(公告)号：US11627307B2

公开(公告)日：2023-04-11

申请号：US17252843

申请日：2018-09-28

Applicant: Intel Corporation

Inventor： Changliang Wang ,  Ximin Zhang ,  Jill Boyce ,  Sang-Hee Lee ,  Scott Janus ,  Yunbiao Lin

IPC: H04N7/12 ,  H04N19/102 ,  H04N19/146

Abstract: Embodiments are generally directed to transport controlled video coding. An embodiment of an apparatus includes one or more processors to process data; a memory to store data, including data for video streaming; and a video processing mechanism including an encoder and a transport mechanism, wherein the video processing mechanism is to generate a prediction of channel throughput for a network channel, encode one or more bitstreams based on the prediction, including encoding a plurality of bitstreams including a first bitstream and a second bitstream if the prediction indicates an increase or decrease in channel throughput and encoding a single bitstream if the prediction indicates a stable channel throughput; and select a bitstream of the one or more bitstreams for a current frame.

公开(公告)号：US11418789B2

公开(公告)日：2022-08-16

申请号：US17125463

申请日：2020-12-17

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Sang-hee Lee ,  Keith W. Rowe

IPC: H04N19/126 ,  H04N19/146 ,  H04N19/172 ,  H04N19/159 ,  H04N19/142

Abstract: Techniques related to coding video using adaptive quantization rounding offsets for use in transform coefficient quantization are discussed. Such techniques may include determining the value of a quantization rounding offset for a picture of a video sequence based on evaluating a maximum coding bit limit of the picture, a quantization parameter of the picture, and parameters corresponding to the video.