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

WO2016184527A1 APPARATUS AND METHOD FOR VIDEO MOTION COMPENSATION 审中-公开
标题翻译：视频运动补偿的装置和方法
公开(公告)号：WO2016184527A1
公开(公告)日：2016-11-24
申请号：PCT/EP2015/061278
申请日：2015-05-21
申请人： HUAWEI TECHNOLOGIES CO., LTD. , ZHAO, Zhijie , LIU, Yiqun , OSTERMANN, Joern
发明人： ZHAO, Zhijie , LIU, Yiqun , OSTERMANN, Joern
IPC分类号： H04N19/105 , H04N19/139 , H04N19/82 , H04N19/567 , H04N19/533 , H04N19/70 , H04N19/61
CPC分类号： H04N19/573 , H04N19/105 , H04N19/117 , H04N19/124 , H04N19/129 , H04N19/13 , H04N19/139 , H04N19/147 , H04N19/176 , H04N19/18 , H04N19/513 , H04N19/533 , H04N19/567 , H04N19/593 , H04N19/65 , H04N19/70 , H04N19/82
摘要： The present invention provides a frame buffer (306) adapted to store at least one reference frame of a video stream, said reference frame being different from a current frame of the video stream, a motion estimation unit (307) adapted to generate a motion vector by estimating motion between a reference block of the reference frame and a current block of the current frame, a blurring filter selection unit (313) adapted to select one of a plurality of blurring filters depending on the orientation of the motion vector, a filtering unit (314) adapted to generate a filtered reference block by applying the selected blurring filter to the reference block, a motion compensation unit (308) adapted to generate a filtered prediction block of the current block on the basis of the current block, the motion vector and the filtered reference block.
摘要翻译：本发明提供了一种帧缓冲器（306），适用于存储视频流的至少一个参考帧，所述参考帧不同于视频流的当前帧，运动估计单元（307）适于产生运动矢量通过估计参考帧的参考块和当前帧的当前块之间的运动，适于根据运动矢量的取向选择多个模糊滤波器之一的模糊滤波器选择单元（313），滤波单元（314），适于通过将所选择的模糊滤波器应用于参考块来生成滤波的参考块;运动补偿单元（308），适于基于当前块生成当前块的滤波预测块，运动矢量和滤波后的参考块。

2. 发明申请

WO2020156670A1 ENCODER- AND DECODER-SIDE DEVICE FOR MACHINE LEARINING BASED SIGNAL CODING 审中-公开
公开(公告)号：WO2020156670A1
公开(公告)日：2020-08-06
申请号：PCT/EP2019/052342
申请日：2019-01-31
申请人： HUAWEI TECHNOLOGIES CO., LTD. , ZHAO, Zhijie
发明人： ZHAO, Zhijie , LAUDE, Thorsten , MEHRINGER, Florian , OSTERMANN, Joern
IPC分类号： H04N19/12 , H04N19/176 , H04N19/46 , H04N19/61
摘要： The present invention relates to the field of image / video coding based on artificial intelligence and machine learning. For machine learning based coding, the present invention provides an encoder side device (100) configured to, for learning: apply a space transformation to a set of prediction errors (101) to obtain a set of space-transformed prediction errors (102) in a reduced space, apply machine learning to the set of space-transformed prediction errors (102) to determine prediction error groups (103a, 103b, 103c) with similar prediction errors from the set of space-transformed prediction errors (102), derive a Karhunen-Loeve-Transform (KLT) (104a, 104b, 104c) for each of the prediction error groups (103a, 103b, 103c) to obtain a group of KLTs (105), and for encoding: encode a given prediction error (106) based on an encoding KLT (107) selected from the group of KLTs (105) and provide the encoded prediction error (108) and information regarding the encoding KLT (109).

3. 发明申请

WO2019110149A1 CLUSTER REFINEMENT FOR TEXTURE SYNTHESIS IN VIDEO CODING 审中-公开
公开(公告)号：WO2019110149A1
公开(公告)日：2019-06-13
申请号：PCT/EP2018/057477
申请日：2018-03-23
申请人： HUAWEI TECHNOLOGIES CO., LTD. , ZHAO, Zhijie
发明人： ZHAO, Zhijie , WANDT, Bastian , LIU, Yiqun , LAUDE, Thorsten , OSTERMANN, Joern , ROSENHAHN, Bodo
IPC分类号： H04N19/48 , H04N19/61 , H04N19/85 , H04N19/90 , H04N19/103 , H04N19/136 , H04N19/17 , H04N19/167 , H04N19/463
CPC分类号： H04N19/85 , H04N19/103 , H04N19/136 , H04N19/167 , H04N19/17 , H04N19/61
摘要： The present disclosure relates to encoding a decoding video employing texture coding. In particular, a texture region is identified within a video picture and a texture patch is determined for said region. Clustering is performed to identify a texture region within the video image. The clustering is further refined. In particular, one or more brightness parameters of a polynomial is determined by fitting the polynomial to the identified texture region. In the identified texture region, samples are detected with a distance to the fitted polynomial exceeding a first threshold and identify a refined texture region as the texture region excluding one or more of the detected samples. Finally, the refined texture region is encoded separately from portions of the video image not belonging to the refined texture region.

4. 发明申请

WO2018099579A1 APPARATUS AND METHOD FOR ENCODING AN IMAGE 审中-公开
公开(公告)号：WO2018099579A1
公开(公告)日：2018-06-07
申请号：PCT/EP2016/079663
申请日：2016-12-02
申请人： HUAWEI TECHNOLOGIES CO., LTD. , ZHAO, Zhijie
发明人： ZHAO, Zhijie , LAUDE, Thorsten , MUNDERLOH, Marco , OSTERMANN, Joern
IPC分类号： H04N19/176 , H04N19/11 , H04N19/136 , H04N19/14
摘要： An apparatus for encoding a block of an image using intra-prediction coding comprising a processor, wherein the processor is configured to: obtain the block of the image; process data associated to the block using a neural network, wherein the neural network is trained to select an intra-prediction mode from a set of pre-determined intra-prediction modes; perform intra-prediction processing for the block according to the selected intra-prediction mode.

5. 发明申请

WO2004097684A1 SYSTEM FOR LOW-LATENCY ANIMATION OF TALKING HEADS 审中-公开
标题翻译：电梯头低位动画系统
公开(公告)号：WO2004097684A1
公开(公告)日：2004-11-11
申请号：PCT/US2004/012402
申请日：2004-04-22
申请人： AT & T CORP. , OSTERMANN, Joern , COSATTO, Eric , GRAF, Hans, Peter
发明人： OSTERMANN, Joern , COSATTO, Eric , GRAF, Hans, Peter
IPC分类号： G06F17/30
CPC分类号： G06F17/30905
摘要： Methods and apparatus for rendering a talking head on a client device are disclosed. The client device has a client cache capable of storing audio/visual data associated with rendering the talking head. The method comprises storing sentences in a client cache of a client device that relate to bridging delays in a dialog, storing sentence templates to be used in dialogs, generating a talking head response to a user inquiry from the client device, and determining whether sentences or stored templates stored in the client cache relate to the talking head response. If the stored sentences or stored templates relate to the talking head response, the method comprises instructing the client device to use the appropriate stored sentence or template from the client cache to render at least a part of the talking head response and transmitting a portion of the talking head response not stored in the client cache, if any, to the client device to render a complete talking head response. If the client cache has no stored data associated with the talking head response, the method comprises transmitting the talking head response to be rendered on the client device.
摘要翻译：公开了一种用于在客户端设备上呈现通话头的方法和设备。客户端设备具有能够存储与呈现话音头相关联的音频/视频数据的客户端高速缓存。该方法包括将客户端设备的客户端缓存中的句子存储在与对话中的桥接延迟相关联，存储要在对话中使用的语句模板，从客户端设备生成对用户的询问头响应，以及确定句子或存储在客户端缓存中的存储模板涉及到通话头响应。如果存储的句子或存储的模板与谈话头响应相关，则该方法包括指示客户端设备使用来自客户端高速缓存的适当存储的句子或模板来呈现至少一部分通话头响应并且传送一部分说话头响应没有存储在客户端缓存中（如果有的话）给客户端设备呈现完整的通话头响应。如果客户端缓存没有与通话头响应相关联的存储数据，则该方法包括传送要在客户端设备上呈现的通话头响应。

6. 发明申请

WO2017097441A1 DEVICES AND METHODS FOR VIDEO CODING USING INTRA PREDICTION 审中-公开
标题翻译：使用帧内预测的视频编码装置和方法
公开(公告)号：WO2017097441A1
公开(公告)日：2017-06-15
申请号：PCT/EP2016/066988
申请日：2016-07-15
申请人： HUAWEI TECHNOLOGIES CO., LTD. , LAUDE, Thorsten
发明人： LAUDE, Thorsten , GRASSHOF, Stella , MUNDERLOH, Marco , OSTERMANN, Joern
IPC分类号： H04N19/593 , H04N19/11 , H04N19/14 , H04N19/176
CPC分类号： H04N19/11 , H04N19/14 , H04N19/176 , H04N19/593
摘要： The invention relates to an apparatus (605) for encoding a video signal, wherein the video signal comprises a plurality of frames, each frame is dividable into a plurality of blocks, each block comprises a plurality of pixels and each pixel is associated with at least one pixel value. The apparatus (605) comprises a prediction module (620) for intra prediction configured to generate a prediction block for a current block on the basis of a reconstructed area comprising at least one already generated reconstructed block adjacent to the current block, wherein the prediction module (620) is configured to detect at least one contour in the reconstructed area, wherein the contour is associated with a subset of the plurality of pixels of the at least one already generated reconstructed block, and to generate the prediction block for the current block on the basis of the at least one contour. Moreover, the invention relates to a corresponding decoding apparatus as well as corresponding methods.
摘要翻译：本发明涉及用于对视频信号进行编码的设备（605），其中视频信号包括多个帧，每个帧可分成多个块，每个块包括多个像素并且每个像素与至少一个像素值相关联。该装置（605）包括用于帧内预测的预测模块（620），该预测模块被配置为基于包括与当前块相邻的至少一个已经生成的重构块的重构区域生成当前块的预测块，其中预测模块（620）被配置为检测所述重建区域中的至少一个轮廓，其中所述轮廓与所述至少一个已经生成的重构块的所述多个像素的子集相关联，并且生成所述当前块的预测块至少一个轮廓的基础。此外，本发明涉及相应的解码设备以及相应的方法。

7. 发明申请

WO2017133753A1 VECTOR QUANTIZATION FOR VIDEO CODING USING CODEBOOK GENERATED BY SELECTED TRAINING SIGNALS 审中-公开
标题翻译：使用选定培训信号生成的代码向视频编码进行矢量量化
公开(公告)号：WO2017133753A1
公开(公告)日：2017-08-10
申请号：PCT/EP2016/052071
申请日：2016-02-01
申请人： HUAWEI TECHNOLOGIES CO., LTD. , GOTTFRIED WILHELM LEIBNIZ UNIVERSITÄT HANNOVER
发明人： ZHAO, Zhijie , JIANTONG, Zhou , LIU, Yiqun , OSTERMANN, Joern
IPC分类号： H04N19/94 , H04N19/176 , H04N19/107 , H04N19/146 , G06T9/00
CPC分类号： H04N19/94 , H04N19/107 , H04N19/146 , H04N19/176
摘要： The present invention relates to an encoder for obtaining training signals configured to train a codebook for vector quantization of a video sequence of subsequent frames, each frame being subdivided into coding blocks. The encoder comprises a scalar quantization unit configured to obtain, for each coding block of one or more training frames of the video sequence, a scalar quantized signal from a prediction error, an entropy coding unit configured to entropy code, for each coding block of each training frame, the scalar quantized signal into an output signal, a data selection unit configured to select, from among the training frames, one or several coding blocks depending on a cost function of their respective output signal, and to obtain, for each selected coding block, a training signal derived from the prediction error of the selected coding block and configured to train the codebook for vector quantization of the video sequence.
摘要翻译：本发明涉及一种用于获得训练信号的编码器，其被配置为训练用于后续帧的视频序列的矢量量化的码本，每个帧被细分成编码块。该编码器包括：标量量化单元，被配置为针对视频序列的一个或多个训练帧的每个编码块从预测误差获得标量量化信号;熵编码单元，被配置为对每个编码块进行熵编码训练帧，标量量化信号转换成输出信号;数据选择单元，被配置为根据它们各自的输出信号的成本函数从训练帧中选择一个或多个编码块，并且针对每个选择的编码块，从所选择的编码块的预测误差导出的训练信号，并且被配置为训练用于视频序列的矢量量化的码本。

8. 发明申请

WO2015136485A1 IMPROVED SCREEN CONTENT AND MIXED CONTENT CODING 审中-公开
标题翻译：改进的屏幕内容和混合内容编码
公开(公告)号：WO2015136485A1
公开(公告)日：2015-09-17
申请号：PCT/IB2015/051821
申请日：2015-03-12
申请人： HUAWEI TECHNOLOGIES CO., LTD.
发明人： LAUDE, Thorsten , MUNDERLOH, Marco , OSTERMANN, Joern
IPC分类号： H04N19/00
CPC分类号： G06T9/00 , H04N19/103 , H04N19/124 , H04N19/167 , H04N19/17 , H04N19/46
摘要： An apparatus comprising a processor configured to obtain mixed content video comprising images comprising computer generated screen content (SC) and natural content (NC), partition the images into SC areas and NC areas, and encode the images by encoding the SC areas with SC coding tools and encoding the NC areas with NC coding tools, and a transmitter coupled to the processor, wherein the transmitter is configured to transmit data to a client device, the data comprising the encoded images and an indication of boundaries of the partition.
摘要翻译：一种装置，包括：处理器，被配置为获得包括计算机生成的屏幕内容（SC）和自然内容（NC）的图像的混合内容视频，将图像分割成SC区域和NC区域，并且通过用SC编码对SC区域进行编码来对图像进行编码工具和使用NC编码工具对NC区域进行编码，以及耦合到处理器的发射机，其中发射机被配置为向客户端设备发送数据，该数据包括编码图像和分区边界的指示。

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