专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明申请

US20170188027A1 Histogram Segmentation Based Local Adaptive Filter for Video Encoding and Decoding 审中-公开
公开(公告)号：US20170188027A1
公开(公告)日：2017-06-29
申请号：US15459043
申请日：2017-03-15
申请人： Intel Corporation
发明人： Lidong Xu , Yi-Jen Chiu , Wenhao Zhang , Hong Jiang
IPC分类号： H04N19/117 , H04N19/147 , H04N19/182
CPC分类号： H04N19/117 , H04N19/136 , H04N19/147 , H04N19/182 , H05K999/99
摘要： Reconstructed picture quality for a video codec system may be improved by categorizing reconstructed pixels into different histogram bins with histogram segmentation and then applying different filters on different bins. Histogram segmentation may be performed by averagely dividing the histogram into M bins or adaptively dividing the histogram into N bins based on the histogram characteristics. Here M and N may be a predefined, fixed, non-negative integer value or an adaptively generated value at encoder side and may be sent to decoder through the coded bitstream.

82. 发明授权

US09571809B2 Simplified depth coding with modified intra-coding for 3D video coding 有权
标题翻译：用于3D视频编码的经过修改的帧内编码的简化深度编码
公开(公告)号：US09571809B2
公开(公告)日：2017-02-14
申请号：US14129455
申请日：2013-08-21
申请人： Intel Corporation
发明人： Zhipin Deng , Yi-Jen Chiu , Lidong Xu , Wenhao Zhang , Yu Han , Xiaoxia Cai , Hong Jiang
IPC分类号： H04N19/597 , H04N13/00
CPC分类号： H04N13/106 , H04N13/161 , H04N19/597
摘要： Systems, mediums, and methods for simplified depth coding for 3D video coding comprises performing modified intra DC coding or modified intra planar coding of at least one coding unit associated with a plurality of pixels and of at least one depth map, and comprising forming a prediction value of the at least one coding unit.
摘要翻译：用于3D视频编码的简化深度编码的系统，介质和方法包括对与多个像素和至少一个深度图相关联的至少一个编码单元执行修改的DC内编码或修改的平面内编码，并且包括形成预测所述至少一个编码单元的值。

83. 发明授权

US09445103B2 Methods and apparatus for adaptively choosing a search range for motion estimation 有权
公开(公告)号：US09445103B2
公开(公告)日：2016-09-13
申请号：US13895939
申请日：2013-05-16
申请人： Intel Corporation
发明人： Lidong Xu , Yi-Jen Chiu
IPC分类号： H04N19/139 , H04N5/14 , H04N19/56 , H04N19/513 , H04N19/57
CPC分类号： H04N19/139 , H04N5/144 , H04N19/513 , H04N19/521 , H04N19/56 , H04N19/57
摘要： Systems, methods, and computer program products that can be used to determine a search range (SR) when performing motion estimation at, for example, a video encoder or decoder. Determining a motion vector for a current block during motion estimation may involve searching within a search window that may reside in a reference frame, or in a previously decoded block that spatially or temporally neighbors the current block. Such a search seeks a motion vector that minimizes a metric, such as a sum of absolute differences between corresponding blocks of reference frames. A motion vector that minimizes such a metric may be a good candidate for use in motion estimation. The search may become more efficient if a search range is determined such that the extent of the search is bounded. A search range may be determined at the block level or at the picture level.

84. 发明授权

US09336460B2 Adaptive motion instability detection in video 有权
标题翻译：视频中的自适应运动不稳定检测
公开(公告)号：US09336460B2
公开(公告)日：2016-05-10
申请号：US14218457
申请日：2014-03-18
申请人： Intel Corporation
发明人： Lidong Xu , Chen Wang , Yi-Jen Chiu , Jong Dae Oh , Heon-Mo Koo
IPC分类号： G06K9/00 , G06K9/62 , H04N5/232
CPC分类号： G06K9/6298 , H04N5/23267
摘要： One or more apparatus and method for adaptively detecting motion instability in video. In embodiments, video stabilization is predicated on adaptive detection of motion instability. Adaptive motion instability detection may entail determining an initial motion instability state associated with a plurality of video frames. Subsequent transitions of the instability state may be detected by comparing a first level of instability associated with a first plurality of the frames to a second level of instability associated with a second plurality of the frames. Image stabilization of received video frames may be toggled first based on the initial instability state, and thereafter based on detected changes in the instability state. Output video frames, which may be stabilized or non-stabilized, may then be stored to a memory. In certain embodiments, video motion instability is scored based on a probability distribution of video frame motion jitter values.
摘要翻译：一种或多种用于自适应地检测视频中的运动不稳定性的装置和方法。在实施例中，视频稳定基于运动不稳定性的自适应检测。自适应运动不稳定性检测可能需要确定与多个视频帧相关联的初始运动不稳定状态。可以通过将与第一多个帧相关联的不稳定性的第一级别与与第二多个帧相关联的第二级不稳定性进行比较来检测不稳定状态的后续转换。首先可以基于初始不稳定状态来切换所接收的视频帧的图像稳定性，然后基于检测到的不稳定状态的变化。然后可以将稳定或不稳定的输出视频帧存储到存储器中。在某些实施例中，基于视频帧运动抖动值的概率分布对视频运动不稳定性进行评分。

85. 发明授权

US09247253B2 In-loop adaptive wiener filter for video coding and decoding 有权
公开(公告)号：US09247253B2
公开(公告)日：2016-01-26
申请号：US14104028
申请日：2013-12-12
申请人： Intel Corporation
发明人： Yi-Jen Chiu , Lidong Xu
IPC分类号： G06K9/40 , H04N19/82 , H04N19/172 , H04N19/61 , H04N19/117 , H04N19/136 , H04N19/177 , H04N19/17
CPC分类号： H04N19/117 , H04N19/136 , H04N19/157 , H04N19/17 , H04N19/172 , H04N19/176 , H04N19/177 , H04N19/18 , H04N19/182 , H04N19/61 , H04N19/65 , H04N19/82 , H04N19/86
摘要： A video encoder may use an adaptive Wiener filter inside the core video encoding loop to improve coding efficiency. In one embodiment, the Wiener filter may be on the input to a motion estimation unit and, in another embodiment, it may be on the output of a motion compensation unit. The taps for the Wiener filter may be determined based on characteristics of at least a region of pixel intensities within a picture. Thus, the filtering may be adaptive in that it varies based on the type of video being processed.

86. 发明申请

US20150350667A1 METHODS AND SYSTEMS FOR MOTION VECTOR DERIVATION AT A VIDEO DECODER 审中-公开
标题翻译：在视频解码器上运动矢量派生的方法和系统
公开(公告)号：US20150350667A1
公开(公告)日：2015-12-03
申请号：US14737437
申请日：2015-06-11
申请人： Intel Corporation
发明人： Yi-Jen Chiu , Lidong Xu , Hong Jiang
IPC分类号： H04N19/52 , H04N19/577
CPC分类号： H04N19/52 , H04N19/44 , H04N19/51 , H04N19/56 , H04N19/577
摘要： Method and apparatus for deriving a motion vector at a video decoder. A block-based motion vector may be produced at the video decoder by utilizing motion estimation among available pixels relative to blocks in one or more reference frames. The available pixels could be, for example, spatially neighboring blocks in the sequential scan coding order of a current frame, blocks in a previously decoded frame, or blocks in a downsampled frame in a lower pyramid when layered coding has been used.
摘要翻译：用于在视频解码器处导出运动矢量的方法和装置。可以通过利用可用像素中相对于一个或多个参考帧中的块的运动估计在视频解码器处产生基于块的运动矢量。当使用分层编码时，可用像素可以是例如当前帧的顺序扫描编码顺序的空间相邻块，先前解码的帧中的块，或者在使用分层编码时在较低金字塔中的下采样帧中的块。

87. 发明申请

US20150304682A1 METHODS AND SYSTEMS TO ESTIMATE MOTION BASED ON RECONSTRUCTED REFERENCE FRAMES AT A VIDEO DECODER 审中-公开
标题翻译：基于视频解码器上重构的参考帧估计运动的方法和系统
公开(公告)号：US20150304682A1
公开(公告)日：2015-10-22
申请号：US14578802
申请日：2014-12-22
申请人： Intel Corporation
发明人： Lidong Xu , Yi-Jen Chiu , Wenhao Zhang
IPC分类号： H04N19/577 , H04N19/44 , H04N19/172 , H04N19/103 , H04N19/139
CPC分类号： H04N19/577 , H04N19/103 , H04N19/137 , H04N19/139 , H04N19/172 , H04N19/44 , H04N19/513 , H04N19/52 , H04N19/57 , H04N19/573 , H04N19/61
摘要： Methods and systems to apply motion estimation (ME) based on reconstructed reference pictures in a B frame or in a P frame at a video decoder. For a P frame, projective ME may be performed to obtain a motion vector (MV) for a current input block. In a B frame, both projective ME and mirror ME may be performed to obtain an MV for the current input block. The ME process can be performed on sub-partitions of the input block, which may reduce the prediction error without increasing the amount of MV information in the bitstream. Decoder-side ME can be applied for the prediction of existing inter frame coding modes, and traditional ME or the decoder-side ME can be adaptively selected to predict a coding mode based on a rate distribution optimization (RDO) criterion.
摘要翻译：基于在B帧或视频解码器的P帧中的重建参考图像应用运动估计（ME）的方法和系统。对于P帧，可以执行投影ME以获得当前输入块的运动矢量（MV）。在B帧中，可以执行投射ME和镜ME两者以获得当前输入块的MV。可以在输入块的子分区上执行ME处理，这可以在不增加比特流中的MV信息的量的情况下减少预测误差。解码器端ME可以应用于现有的帧间编码模式的预测，并且传统的ME或解码器侧的ME可以被自适应地选择以基于速率分布优化（RDO）准则来预测编码模式。

88. 发明申请

US20150181216A1 INTER-LAYER PIXEL SAMPLE PREDICTION 审中-公开
标题翻译：层间像素样本预测
公开(公告)号：US20150181216A1
公开(公告)日：2015-06-25
申请号：US14640356
申请日：2015-03-06
申请人： Intel Corporation
发明人： Wenhao Zhang , Yi-Jen Chiu , Lidong Xu , Yu Han , Zhipin Deng , Xiaoxia Cai
IPC分类号： H04N19/159 , H04N19/182 , H04N19/513 , H04N19/105
CPC分类号： H04N19/159 , H04N19/105 , H04N19/117 , H04N19/136 , H04N19/147 , H04N19/176 , H04N19/182 , H04N19/30 , H04N19/33 , H04N19/34 , H04N19/503 , H04N19/513 , H04N19/59 , H04N19/80
摘要： Systems, devices and methods are described including performing scalable video coding using inter-layer pixel sample prediction. Inter-layer pixel sample prediction in an enhancement layer coding unit, prediction unit, or transform unit may use reconstructed pixel samples obtained from a base layer or from a lower enhancement layer. The pixel samples may be subjected to upsample filtering and/or refinement filtering. The upsample or refinement filter coefficients may be predetermined or may be adaptively determined.
摘要翻译：描述了使用层间像素样本预测执行可缩放视频编码的系统，设备和方法。增强层编码单元，预测单元或变换单元中的层间像素样本预测可以使用从基本层或较低增强层获得的重建像素样本。可以对像素样本进行上采样滤波和/或细化滤波。上采样或细化滤波器系数可以是预定的或可以被自适应地确定。

89. 发明申请

US20230054523A1 ENHANCING 360-DEGREE VIDEO USING CONVOLUTIONAL NEURAL NETWORK (CNN)-BASED FILTER 有权
公开(公告)号：US20230054523A1
公开(公告)日：2023-02-23
申请号：US17793348
申请日：2020-02-17
申请人： Intel Corporation
发明人： Huan Dou , Lidong Xu , Xiaoxia Cai , Chen Wang , Yi-Jen Chiu
IPC分类号： H04N5/232 , G06T5/00 , H04N19/597 , H04N19/80 , H04N19/86
摘要： An example apparatus for enhancing video includes a decoder to decode a received 360-degree projection format video bitstream to generate a decoded 360-degree projection format video. The apparatus also includes a viewport generator to generate a viewport from the decoded 360-degree projection format video. The apparatus further includes a convolutional neural network (CNN)-based filter to remove an artifact from the viewport to generate an enhanced image. The apparatus further includes a displayer to send the enhanced image to a display.

90. 发明申请

US20220109889A1 APPARATUS, ARTICLES OF MANUFACTURE, AND METHODS FOR IMPROVED ADAPTIVE LOOP FILTERING IN VIDEO ENCODING 有权
公开(公告)号：US20220109889A1
公开(公告)日：2022-04-07
申请号：US17553460
申请日：2021-12-16
申请人： Intel Corporation
发明人： Ximin Zhang , Yi-Jen Chiu , Keith Rowe
IPC分类号： H04N19/82 , H04N19/147 , H04N19/107 , H04N19/117 , G06N20/00
摘要： 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.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式