专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022261849A1 METHOD AND SYSTEM OF AUTOMATIC CONTENT-DEPENDENT IMAGE PROCESSING ALGORITHM SELECTION 审中-公开
公开(公告)号：WO2022261849A1
公开(公告)日：2022-12-22
申请号：PCT/CN2021/100315
申请日：2021-06-16
申请人： INTEL CORPORATION , WANG, Chen , DOU, Huan , LEE, Sang-Hee , CHIU, Yi-Jen , XU, Lidong
发明人： WANG, Chen , DOU, Huan , LEE, Sang-Hee , CHIU, Yi-Jen , XU, Lidong
IPC分类号： H04N7/01 , H04N5/265 , H04N19/109 , H04N19/176 , G06T3/40
摘要： Embodiments in accordance with this disclosure provide a system and method for automatic content-dependent image processing algorithm selection. The method can include obtaining one or more frames of a video sequence; dividing the individual frames into sections; automatically determining whether to apply at least one non-neural network image processing algorithm or at least one neural network image processing algorithm to the individual sections depending on at least one content-based criterium; and applying at least one determined algorithm to at least one of the sections to process the image data of the sections.

2. 发明申请

WO2017127167A1 LONG TERM REFERENCE PICTURE CODING 审中-公开
标题翻译：长期参考图像编码
公开(公告)号：WO2017127167A1
公开(公告)日：2017-07-27
申请号：PCT/US2016/065202
申请日：2016-12-06
申请人： INTEL CORPORATION
发明人： ZHANG, Ximin , LEE, Sang-Hee , RYZHOV, Dmitry, E.
IPC分类号： H04N19/58 , H04N19/124 , H04N19/70 , H04N19/105 , H04N19/11 , H04N19/147 , H04N19/42
CPC分类号： H04N19/58 , H04N19/124 , H04N19/126 , H04N19/142 , H04N19/146 , H04N19/159 , H04N19/172 , H04N19/177 , H04N19/593 , H04N19/70
摘要： Techniques related to long reference picture video coding are discussed. Such techniques may include determining long term reference pictures for a sequence of pictures, adjusting quantization parameters for the long term reference pictures, coding the individual long term reference picture based on the coding quantization parameter, generating a reference picture list syntax comprising an indicator to insert the individual long term reference picture into a long term reference picture list when the individual long term reference picture is replaced in a short term reference picture list by another picture, and providing the coded individual long term reference picture and the reference picture list syntax in a bitstream.
摘要翻译：讨论了与长参考图像视频编码有关的技术。这些技术可以包括确定图片序列的长期参考图片，调整长期参考图片的量化参数，基于编码量化参数对个体长期参考图片进行编码，生成包括插入指示符的参考图片列表语法当个别长期参考图片在短期参考图片列表中被另一图片替换时，将个体长期参考图片转换为长期参考图片列表，并且将编码个体长期参考图片和参考图片列表语法提供给比特流中。

3. 发明申请

WO2013081615A1 MOTION ESTIMATION METHODS FOR RESIDUAL PREDICTION 审中-公开
标题翻译：运动估计方法进行残差预测
公开(公告)号：WO2013081615A1
公开(公告)日：2013-06-06
申请号：PCT/US2011/062778
申请日：2011-12-01
申请人： INTEL CORPORATION , LEE, Sang-Hee , FU, Fangwen , LEI, Zhijun
发明人： LEE, Sang-Hee , FU, Fangwen , LEI, Zhijun
IPC分类号： H04N7/32 , H04N7/26 , H04N7/36
CPC分类号： H04N19/51 , H04N19/132 , H04N19/184 , H04N19/30 , H04N19/42 , H04N19/43 , H04N19/463
摘要： Systems, apparatus and methods are described including determining a first value by reducing a bit-length of a reference pixel value and adding a first predetermined value to the result and determining a second value by subtracting a residual pixel value from a current pixel value to generate a difference value, reducing a bit-length of the difference value and adding the first predetermined value to the result. The range of the second value may then be clipped by setting the second value to zero when the second value is equal to or less than a second predetermined value and setting the second value to a third predetermined value when the second value is equal to or greater than a fourth predetermined value. The first value and the second value may then be used for inter-layer residual prediction in Scalable Video Coding (SVC) systems.
摘要翻译：描述了系统，装置和方法，包括通过减小参考像素值的比特长度并将第一预定值加到结果来确定第一值，并通过从当前像素值减去残差像素值来产生第二值以产生差值，减小差值的位长并将第一预定值加到结果上。然后可以通过在第二值等于或小于第二预定值时将第二值设置为零来限制第二值的范围，并且当第二值等于或大于第二值时将第二值设置为第三预定值超过第四预定值。然后可以将第一值和第二值用于可伸缩视频编码（SVC）系统中的层间残差预测。

4. 发明申请

WO2022108653A1 VIDEO ENCODING RATE CONTROL FOR INTRA AND SCENE CHANGE FRAMES USING MACHINE LEARNING 审中-公开
公开(公告)号：WO2022108653A1
公开(公告)日：2022-05-27
申请号：PCT/US2021/050887
申请日：2021-09-17
申请人： INTEL CORPORATION
发明人： ZHANG, Ximin , LEE, Sang-Hee , ROWE, Keith W.
IPC分类号： H04N19/159 , H04N19/70 , H04N19/30 , H04N19/176 , G06N3/08 , H04N19/179
摘要： 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.

5. 发明申请

WO2020061990A1 TRANSPORT CONTROLLED VIDEO CODING 审中-公开
公开(公告)号：WO2020061990A1
公开(公告)日：2020-04-02
申请号：PCT/CN2018/108208
申请日：2018-09-28
申请人： INTEL CORPORATION , WANG, Changliang , ZHANG, Ximin , BOYCE, Jill , LEE, Sang-Hee , JANUS, Scott , LIN, Yunbiao
发明人： WANG, Changliang , ZHANG, Ximin , BOYCE, Jill , LEE, Sang-Hee , JANUS, Scott , LIN, Yunbiao
IPC分类号： H04N7/00 , H04N19/00
摘要： 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.

6. 发明申请

WO2017127168A1 TRANSFORM UNIT SIZE DETERMINATION FOR VIDEO CODING 审中-公开
标题翻译：用于视频编码的变换单元尺寸确定
公开(公告)号：WO2017127168A1
公开(公告)日：2017-07-27
申请号：PCT/US2016/065203
申请日：2016-12-06
申请人： INTEL CORPORATION
发明人： ZHANG, Ximin , LEE, Sang-Hee
IPC分类号： H04N19/119 , H04N19/11 , H04N19/124 , H04N19/14 , H04N19/139 , H04N19/70
CPC分类号： H04N19/176 , H04N19/119 , H04N19/122 , H04N19/14
摘要： 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.
摘要翻译：讨论了与用于视频编码的变换单元大小确定有关的技术。这样的技术可以包括将诸如编码单元的视频的图片的单元的单独预测残差与自适应阈值进行比较，并且如果任何预测残差超过自适应阈值，则分割与该单元对应的变换单元。

7. 发明申请

WO2016018493A1 GOLDEN FRAME SELECTION IN VIDEO CODING 审中-公开
标题翻译： GOLDEN FRAME选择在视频编码
公开(公告)号：WO2016018493A1
公开(公告)日：2016-02-04
申请号：PCT/US2015/030631
申请日：2015-05-13
申请人： INTEL CORPORATION
发明人： ZHANG, Ximin , LEE, Sang-Hee
IPC分类号： H04N19/147 , H04N19/172 , H04N19/176 , H04N19/50
CPC分类号： H04N19/142 , H04N19/105 , H04N19/115 , H04N19/124 , H04N19/137 , H04N19/139 , H04N19/14 , H04N19/147 , H04N19/159 , H04N19/172 , H04N19/503 , H04N19/58
摘要： 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.
摘要翻译：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。

8. 发明申请

WO2016003548A1 TECHNIQUES FOR PROCESSING A VIDEO FRAME BY A VIDEO ENCODER 审中-公开
标题翻译：通过视频编码器处理视频帧的技术
公开(公告)号：WO2016003548A1
公开(公告)日：2016-01-07
申请号：PCT/US2015/031296
申请日：2015-05-18
申请人： INTEL CORPORATION
发明人： RHEE, Changwon D. , CHEUNG, Kin-Hang , LEE, Sang-Hee , LEI, Zhi jun , RYZHOV, Dmitry E. , ZHU, Xinglei
IPC分类号： H04N19/176 , H04N19/177 , H04N19/50
CPC分类号： H04N19/436
摘要： Various embodiments are generally directed to an apparatus, method and other techniques for divide a frame comprising pixels into a number of macroblocks, each macroblock comprising a number of pixels within four macroblock boundaries. Various embodiments may also include creating at least two regions having a plurality of macroblocks by dividing the frame along macroblock boundaries and generating wave front groups based on the macroblocks in each region, each wave front group from each region comprising one or more macroblocks to process in parallel.
摘要翻译：各种实施例通常涉及用于将包括像素的帧划分成多个宏块的装置，方法和其他技术，每个宏块包括四个宏块边界内的多个像素。各种实施例还可以包括通过沿着宏块边界划分帧来创建具有多个宏块的至少两个区域，并且基于每个区域中的宏块生成波前组，每个区域包括一个或多个宏块以进行处理平行。

9. 发明申请

WO2014193630A1 QUANTIZATION OFFSET AND COST FACTOR MODIFICATION FOR VIDEO ENCODING 审中-公开
标题翻译：量化偏移和成本因素修改视频编码
公开(公告)号：WO2014193630A1
公开(公告)日：2014-12-04
申请号：PCT/US2014/037532
申请日：2014-05-09
申请人： INTEL CORPORATION
发明人： LEI, Zhijun Ryan , LEE, Sang-Hee
IPC分类号： H04N19/124 , H04N19/102 , H04N19/593
CPC分类号： H04N19/124 , H04N19/126 , H04N19/136 , H04N19/137 , H04N19/14 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/60
摘要： Methods, apparatus, systems and articles of manufacture to perform quantization offset and/or cost factor modification for video encoding are disclosed. Some example methods for video encoding disclosed herein include adjusting a quantization offset to quantize a transform coefficient representative of a pixel block in a frame of a video sequence. For example, the quantization offset can be adjusted based on a quantization parameter obtained to quantize the transform coefficient. Some such example methods also include quantizing the transform coefficient according to the quantization parameter and the quantization offset. Some example methods for video encoding disclosed herein additionally or alternatively include adjusting a cost factor based on a characteristic of a pixel block in a frame of a video sequence. Some such example methods also include determining, based on the cost factor, a cost associated with encoding the pixel block according to a first encoding mode.
摘要翻译：公开了用于执行视频编码的量化偏移和/或成本因子修改的方法，装置，系统和制造。本文公开的用于视频编码的一些示例性方法包括调整量化偏移以量化表示视频序列的帧中的像素块的变换系数。例如，可以基于获得的用于量化变换系数的量化参数来调整量化偏移。一些这样的示例方法还包括根据量化参数和量化偏移量化变换系数。本文公开的视频编码的一些示例性方法另外地或替代地包括基于视频序列的帧中的像素块的特性来调整成本因子。一些这样的示例方法还包括基于成本因素来确定与根据第一编码模式对像素块进行编码相关联的成本。

10. 发明申请

WO2013032512A1 MULTIVIEW VIDEO CODING SCHEMES 审中-公开
标题翻译：多视频编码方案
公开(公告)号：WO2013032512A1
公开(公告)日：2013-03-07
申请号：PCT/US2011/064615
申请日：2011-12-13
申请人： INTEL CORPORATION , LEE, Sang-Hee , ZHU, Xinglei , JIANG, Hong
发明人： LEE, Sang-Hee , ZHU, Xinglei , JIANG, Hong
IPC分类号： H04N7/26
CPC分类号： H04N19/00769 , H04N19/51 , H04N19/597 , H04N19/70
摘要： Systems, devices and methods are described including determining an inter-view coding mode for at least a portion of an image frame, specifying a corresponding value of an inter-view coding mode indicator, and providing the mode indicator in a bitstream that includes an encoded motion vector associated with the image frame portion. A first value of the mode indicator corresponds to a first inter-view coding mode where the encoded motion vector includes components in multiple dimensions. A second value of the mode indicator corresponds to a second inter-view coding mode where the encoded motion vector components include components in only one dimension.
摘要翻译：描述了系统，设备和方法，包括确定图像帧的至少一部分的视角间编码模式，指定视频间编码模式指示符的相应值，以及将模式指示符提供给包括编码的与图像帧部分相关联的运动矢量。模式指示符的第一值对应于第一视频间编码模式，其中编码的运动矢量包括多个维度的分量。模式指示符的第二值对应于第二视角间编码模式，其中编码的运动矢量分量仅包括一个维度中的分量。

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