公开(公告)号：US20170214913A1

公开(公告)日：2017-07-27

申请号：US15004779

申请日：2016-01-22

Applicant: INTEL CORPORATION

Inventor： Ximin Zhang ,  Sang-Hee Lee

IPC: H04N19/115 ,  H04N19/176 ,  H04N19/137 ,  H04N19/13

Abstract: Techniques related to transform unit size determination for video coding are discussed. Such techniques may include comparing individual prediction residues of a unit of a picture of video such as a coding unit to an adaptive threshold and splitting a transform unit corresponding to the unit if any of the prediction residues exceed the adaptive threshold.

公开(公告)号：US20160366414A1

公开(公告)日：2016-12-15

申请号：US14737795

申请日：2015-06-12

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Sang-Hee Lee

IPC: H04N19/132 ,  H04N19/177 ,  H04N19/16 ,  H04N19/503 ,  H04N19/126 ,  H04N19/184 ,  H04N19/187

CPC classification number: H04N19/132 ,  H04N19/103 ,  H04N19/126 ,  H04N19/147 ,  H04N19/149 ,  H04N19/16 ,  H04N19/172 ,  H04N19/177 ,  H04N19/184 ,  H04N19/187 ,  H04N19/503

Abstract: Techniques related to video coding with low bitrates are discussed. Such techniques may include skipping coding of a picture of a group of pictures when an estimated coding bit cost of the picture is greater than an available coding bit limit for the picture and, when the estimated coding bit cost is not greater than the available coding bit limit, determining the coding skip indicator based on a picture type of the individual picture and a picture structure of the group of pictures.

Abstract translation: 讨论了与低比特率的视频编码相关的技术。 这样的技术可以包括当图像的估计编码比特成本大于图像的可用编码比特限制时跳过一组图像的图像的编码，并且当估计的编码比特成本不大于可用编码比特 限制，基于各个图像的图像类型和图像组的图像结构来确定编码跳过指示符。

公开(公告)号：US20160173875A1

公开(公告)日：2016-06-16

申请号：US14567600

申请日：2014-12-11

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Sang-Hee Lee

IPC: H04N19/124 ,  H04N19/115 ,  H04N19/436 ,  H04N19/15 ,  H04N19/152 ,  H04N19/172

CPC classification number: H04N19/124 ,  H04N19/115 ,  H04N19/15 ,  H04N19/152 ,  H04N19/172 ,  H04N19/436

Abstract: Systems and methods for determining a target number of bits (target bitrate) for encoding a frame of video that will satisfy a buffer constraint in a parallel video encoder. The quantization parameter (QP) for a given encoding process may be determined for the frame based on the target bitrate to maintain a suitable average bitrate. In some embodiments, the bitrate used for one or more prior frame is estimated. In some embodiments, a buffer fullness update is made based on an estimated bitrate. In some embodiments, a bitrate to target for each frame is determined based on the frame type, estimated bitrate of a prior frame(s), and the updated buffer fullness.

Abstract translation: 用于确定用于对将要满足并行视频编码器中的缓冲器约束的视频帧进行编码的目标位数（目标比特率）的系统和方法。 可以基于目标比特率来确定针对帧的给定编码处理的量化参数（QP）以维持合适的平均比特率。 在一些实施例中，估计用于一个或多个先前帧的比特率。 在一些实施例中，基于估计的比特率进行缓冲器充满度更新。 在一些实施例中，基于帧类型，先前帧的估计比特率和更新的缓冲区饱和度来确定针对每个帧的比特率。

公开(公告)号：US12192478B2

公开(公告)日：2025-01-07

申请号：US17764162

申请日：2019-11-14

Applicant: Intel Corporation

Inventor： Yunbiao Lin ,  Changliang Wang ,  Ximin Zhang ,  Fan He ,  Jill Boyce ,  Sri Ranjan Srikantam

IPC: H04N19/146 ,  H04N19/142 ,  H04N19/172 ,  H04N19/184

Abstract: An example apparatus for adaptively encoding video frames includes a network analyzer to predict an instant bitrate based on channel throughput feedback received from a network. The apparatus also includes a content analyzer to generate ladder info based on a received frame. The apparatus further includes an adaptive decision executer to determine a frame rate, a video resolution, and a target frame size based on the predicted instant bitrate and the ladder outputs. The apparatus further includes an encoder to encode the frame based on the frame rate, the video resolution, and the target frame size.

公开(公告)号：US20240357138A1

公开(公告)日：2024-10-24

申请号：US18665022

申请日：2024-05-15

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：US20240348801A1

公开(公告)日：2024-10-17

申请号：US18753360

申请日：2024-06-25

Applicant: Intel Corporation

Inventor： Sebastian Possos ,  Yi-jen Chiu ,  Ximin Zhang

IPC: H04N19/177 ,  H04N19/136 ,  H04N19/172

CPC classification number: H04N19/177 ,  H04N19/136 ,  H04N19/172

Abstract: Using a fixed group of pictures (GOP) size in video encoding significantly hinders compression efficiency due to its inability to adapt to the dynamic nature of video content. While encoding leverages spatio-temporal redundancy within a GOP for compression, a predetermined size fails to capture the varying complexity of scenes. This leads to wasted bits in low-motion segments and insufficient reference frame variation for high-motion areas, resulting in visual artifacts and reduced compression efficiency. To address this limitation, a GOP size recommendation engine involving machine learning models can determine frame-level GOP size recommendations based on pre-encoder frame statistics. The frame-level GOP size recommendations are used to adapt the GOP size for encoding video frames.

公开(公告)号：US20240259568A1

公开(公告)日：2024-08-01

申请号：US18635840

申请日：2024-04-15

Applicant: Intel Corporation

Inventor： Qian Xu ,  Ximin Zhang ,  Yi-jen Chiu

IPC: H04N19/147 ,  H04N19/105 ,  H04N19/137 ,  H04N19/176

CPC classification number: H04N19/147 ,  H04N19/105 ,  H04N19/137 ,  H04N19/176

Abstract: Different approaches for reducing complexity and computations in inter-prediction encoding are described. The approaches may involve one or more of quantization parameter and motion information being used to make a precision decision at a picture level that can improve compression efficiency. The approaches may involve finding prediction costs for the motion vector difference candidates and then performing rate-distortion optimization using the selected motion vector difference candidate having the lowest prediction cost. Prediction costs may be determined using sums of absolute transformed differences, which can be calculated efficiently in hardware. The rate-distortion cost of using merge mode with motion vector difference with the selected motion vector difference candidate may be compared against one or more other rate-distortion costs. In addition, in some scenarios, the approaches may involve finding prediction costs for a subset of the motion vector difference candidates to further reduce computations.

公开(公告)号：US20240107078A1

公开(公告)日：2024-03-28

申请号：US18525444

申请日：2023-11-30

Applicant: Intel Corporation

Inventor： Minzhi Sun ,  Ximin Zhang ,  Yi-jen Chiu

IPC: H04N19/86 ,  H04N19/124 ,  H04N19/176

CPC classification number: H04N19/86 ,  H04N19/124 ,  H04N19/176

Abstract: Methods, articles, and systems of image processing comprise obtaining image data of frames of a video sequence. The method also includes determining multiple reference frames of a current frame in the video sequence. The multiple reference frames each have at least one motion compensated (MC) block of image data. Also, the method then includes generating a weight that factors noise, distortion variance, and dispersion distribution between the same MC block position and the current block. Thereafter, the method includes generating denoised filtered image data comprising applying one of the weights to the image data of the motion compensated (MC) block.

公开(公告)号：US11863755B2

公开(公告)日：2024-01-02

申请号：US17560095

申请日：2021-12-22

Applicant: Intel Corporation

Inventor： Sebastian Possos ,  Ximin Zhang ,  Changliang Wang

IPC: H04N19/124 ,  H04N19/137 ,  H04N19/176

CPC classification number: H04N19/137 ,  H04N19/124 ,  H04N19/176

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed. Example apparatus disclosed herein are to process features extracted from first and second downscaled image frames to determine block classifications for respective blocks of the first and the second downscaled image frames. Disclosed example apparatus are also to generate a map based on the block classifications, the map including values representative of amounts of change associated with blocks of the second downscaled image frame and corresponding blocks of the first downscaled image frame. Disclosed example apparatus are further to adjust a quantization parameter of a full-scale image frame based on the map, the full-scale image frame corresponding to the at least one of the first or the second downscaled image frames.

公开(公告)号：US20220109889A1

公开(公告)日：2022-04-07

申请号：US17553460

申请日：2021-12-16

Applicant: Intel Corporation

Inventor： Ximin Zhang ,  Yi-Jen Chiu ,  Keith Rowe

IPC: H04N19/82 ,  H04N19/147 ,  H04N19/107 ,  H04N19/117 ,  G06N20/00

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve video encoding. An example apparatus includes at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to identify a first video frame as a critical video frame with respect to a previous video frame, generate filter coefficients of a video filter based on pixel data of the first video frame or pixel data of a previous critical video frame, and encode the first video frame with the filter coefficients.