-
公开(公告)号:US09549188B2
公开(公告)日:2017-01-17
申请号:US14446556
申请日:2014-07-30
Applicant: Intel Corporation
Inventor: Ximin Zhang , Sang-Hee Lee
IPC: H04N19/142 , H04N19/124 , H04N19/172 , H04N19/147 , H04N19/115 , H04N19/105 , H04N19/503 , H04N19/139 , H04N19/14
CPC classification number: H04N19/142 , H04N19/105 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/139 , H04N19/14 , H04N19/147 , H04N19/159 , H04N19/172 , H04N19/503 , H04N19/58
Abstract: Techniques related to designating golden frames and to determining frame sizes and/or quantization parameters golden and non-golden frames for video coding are discussed. Such techniques may include designating an frame as a golden frame or a non-golden frame based on whether the frame is a scene change frame, a distance of the frame to a previous golden frame, and an average temporal distortion of the frame and determining a frame size and/or quantization parameter for the frame based on the designation and a temporal distortion of the frame.
Abstract translation: 讨论了与指定黄金帧并确定帧大小和/或量化参数相关的技术,用于视频编码的黄金和非黄金帧。 这样的技术可以包括基于帧是场景改变帧,帧到先前黄金帧的距离以及帧的平均时间失真来确定框架作为黄金帧或非黄金帧来指定帧,并且确定 基于帧的指定和时间失真的帧的帧大小和/或量化参数。
-
公开(公告)号:US20250047851A1
公开(公告)日:2025-02-06
申请号:US18921274
申请日:2024-10-21
Applicant: Intel Corporation
Inventor: Ximin Zhang , Changliang Wang , Sang-hee Lee , Keith Rowe
IPC: H04N19/124 , H04N19/119 , H04N19/167 , H04N19/172
Abstract: Techniques related to adaptive quality boosting for low latency video coding are discussed. Such techniques include segmenting each of a number of temporally adjacent video frames into unique high encode quality regions and encoding each of the video frames by applying a coding quality boost to the high encode quality regions relative to other regions of the video frames.
-
公开(公告)号:US12166986B2
公开(公告)日:2024-12-10
申请号:US17121284
申请日:2020-12-14
Applicant: Intel Corporation
Inventor: Ximin Zhang , Changliang Wang , Sang-hee Lee , Keith Rowe
IPC: H04N19/124 , H04N19/119 , H04N19/167 , H04N19/172
Abstract: Techniques related to adaptive quality boosting for low latency video coding are discussed. Such techniques include segmenting each of a number of temporally adjacent video frames into unique high encode quality regions and encoding each of the video frames by applying a coding quality boost to the high encode quality regions relative to other regions of the video frames.
-
公开(公告)号:US12120312B2
公开(公告)日:2024-10-15
申请号:US16950367
申请日:2020-11-17
Applicant: Intel Corporation
Inventor: Ximin Zhang , Sang-hee Lee , Keith W. Rowe
IPC: H04N19/159 , G06N3/084 , H04N19/176 , H04N19/179 , H04N19/30 , H04N19/70
CPC classification number: H04N19/159 , G06N3/084 , H04N19/176 , H04N19/179 , H04N19/70 , H04N19/30
Abstract: Techniques related to quantization parameter estimation for coding intra and scene change frames are discussed. Such techniques include generating features based on an intra or scene change frame including a proportion of smooth blocks and one or both of a measure of block variance and a prediction distortion, and applying a machine learning model to generate an estimated quantization parameter for encoding the intra or scene change frame.
-
公开(公告)号:US20240283952A1
公开(公告)日:2024-08-22
申请号:US18636941
申请日:2024-04-16
Applicant: Intel Corporation
Inventor: Minzhi Sun , Ximin Zhang , Yi-jen Chiu , James Holland
IPC: H04N19/189 , H04N19/176 , H04N19/186 , H04N19/46
CPC classification number: H04N19/189 , H04N19/176 , H04N19/186 , H04N19/46
Abstract: A lightweight but effective adaptive coding tool selection system with content classification can be implemented to reduce complexity and maintain quality in a video encoder. Content classification may classify a current frame between at least three classifications: screen content, weak screen content, and natural content. Content classification may make use of two statistics, e.g., color number and variance, of blocks that are 8×8 pixels or larger in size. The statistics may be used to calculate three frame-level statistics, e.g., proportion/percentage of blocks with few colors, proportion/percentage of blocks with zero variance, and proportion/percentage of blocks with big/large variance. The frame-level statistics are used to classify the current frame. Based on the classification, coding tool control flags or control signals may be generated accordingly to configure the encoder to, e.g., turn on or off certain coding tools, and/or use certain parameter values for the coding tools.
-
公开(公告)号:US11445220B2
公开(公告)日:2022-09-13
申请号:US16901910
申请日:2020-06-15
Applicant: Intel Corporation
Inventor: Ximin Zhang , Sang-Hee Lee , Keith W. Rowe
IPC: H04N19/82 , H04N19/117 , H04N19/136 , H04N19/172 , H04N19/182
Abstract: Techniques related to selecting restoration filter coefficients for 2-dimensional loop restoration filters for super resolution video coding are discussed. Such techniques include upscaling reconstructed video frames along only a first dimension and selecting filter coefficients for portions of the frame by an evaluation that, for each pixel of the portion, uses only pixel values that are aligned with the first dimension. Selection of filter coefficients for the second dimension may be skipped or made using only a subset of available filter coefficients.
-
公开(公告)号:US20220116622A1
公开(公告)日:2022-04-14
申请号:US17560095
申请日:2021-12-22
Applicant: Intel Corporation
Inventor: Sebastian Possos , Ximin Zhang , Changliang Wang
IPC: H04N19/137 , H04N19/176 , H04N19/124
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:US20200267396A1
公开(公告)日:2020-08-20
申请号:US16869053
申请日:2020-05-07
Applicant: Intel Corporation
Inventor: Ximin Zhang , Sang-Hee Lee , Keith Rowe
IPC: H04N19/196 , H04N19/177 , H04N19/124 , H04N19/176 , H04N19/14
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:US10555002B2
公开(公告)日:2020-02-04
申请号:US15002697
申请日:2016-01-21
Applicant: INTEL CORPORATION
Inventor: Ximin Zhang , Sang-Hee Lee , Dmitry E. Ryzhov
IPC: H04N19/58 , H04N19/126 , H04N19/146 , H04N19/177 , H04N19/593 , H04N19/70
Abstract: Techniques related to long term reference picture video coding are discussed. Such techniques include determining long term reference pictures for a sequence of pictures, adjusting the quantization parameters for the long term reference pictures based on temporal correlations for pictures temporally neighboring and including the long term reference pictures, and managing reference picture lists including the long term reference pictures.
-
20.
公开(公告)号:US10341658B2
公开(公告)日:2019-07-02
申请号:US15419493
申请日:2017-01-30
Applicant: Intel Corporation
Inventor: Ya-Ti Peng , Yu-Ting Li , Ximin Zhang , Yi-Jen Chiu , Sang-Hee Lee
IPC: H04N19/117 , H04N19/137 , H04N19/182 , H04N19/154
Abstract: Techniques related to video pre-processing for video coding are discussed. Such video pre-processing techniques may include applying adaptive temporal and spatial filtering to pixel values of video frames of input video to generate pre-processed video such that the adaptive temporal and spatial filtering includes blending spatial and temporal filtering of the individual pixel value when the block of pixels is a non-motion block and spatial-only filtering the individual pixel value when the block of pixels is a motion block.
-
-
-
-
-
-
-
-
-