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

WO2023089230A2 AN APPARATUS, A METHOD AND A COMPUTER PROGRAM FOR VIDEO CODING AND DECODING 审中-公开
公开(公告)号：WO2023089230A2
公开(公告)日：2023-05-25
申请号：PCT/FI2022/050738
申请日：2022-11-09
申请人： NOKIA TECHNOLOGIES OY
发明人： GHAZNAVI YOUVALARI, Ramin , ASTOLA, Pekka , LAINEMA, Jani , AMINLOU, Alireza
摘要： A method comprising: obtaining an image block unit comprising samples in color channels of one or two chrominance channels and one luminance channel; reconstructing samples of said luminance channels of the image block unit; determining parameters for at least one prediction model for predicting samples of at least one channel of image block unit using a prediction model based on one or more of reference samples in a neighboring block in current channel/ frame, one or more of the reference samples in the neighboring of the co-located block in reference channel/frame; and one or more of the reference samples inside the co-located block in reference channel/frame; and determining said at least one prediction model as a polynomial and/or exponential prediction model.

2. 发明申请

WO2022195409A1 METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR END-TO-END LEARNED PREDICTIVE CODING OF MEDIA FRAMES 审中-公开
公开(公告)号：WO2022195409A1
公开(公告)日：2022-09-22
申请号：PCT/IB2022/052115
申请日：2022-03-09
申请人： NOKIA TECHNOLOGIES OY
发明人： ZOU, Nannan , ZHANG, Honglei , CRICRÌ, Francesco , REZAZADEGAN TAVAKOLI, Hamed , GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/577 , G06N3/04
摘要： Various embodiments provide an apparatus, a method and a computer program product for end- to-end learned predictive coding of media frames. An example apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode one or more media frames for at least one neural network; wherein an inter-frame codec is applied to at least one media frame of the one or more media frames; and wherein a first decoded reference frame and a second decoded reference frame refer to reference frames for the at least one media frame.

3. 发明申请

WO2018002425A3 AN APPARATUS, A METHOD AND A COMPUTER PROGRAM FOR VIDEO CODING AND DECODING 审中-公开
公开(公告)号：WO2018002425A3
公开(公告)日：2018-01-04
申请号：PCT/FI2017/050448
申请日：2017-06-15
申请人： NOKIA TECHNOLOGIES OY
发明人： HANNUKSELA, Miska , LAINEMA, Jani , AMINLOU, Alireza , GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/167 , H04N19/59 , G06T3/40 , H04N5/232 , G03B37/00
摘要： A method for video decoding comprising: decoding, from a bitstream, a first encoded region of a first equirectangular picture into a first preliminary reconstructed region (760); forming a first reconstructed region from the first preliminary reconstructed region, wherein the forming comprises downsampling and rearranging the first preliminary reconstructed region, wherein the rearranging comprises relocating and one or both of rotating and mirroring (762); and decoding at least a second region, wherein the first reconstructed region is used as a reference for prediction in decoding the at least second region (764) and the second region either belongs to a second picture and is spatially collocated with the first reconstructed region or belongs to the first picture.

4. 发明申请

WO2023073281A1 A METHOD, AN APPARATUS AND A COMPUTER PROGRAM PRODUCT FOR VIDEO CODING 审中-公开
公开(公告)号：WO2023073281A1
公开(公告)日：2023-05-04
申请号：PCT/FI2022/050663
申请日：2022-10-05
申请人： NOKIA TECHNOLOGIES OY
发明人： ZHANG, Honglei , CRICRÌ, Francesco , HANNUKSELA, Miska, Matias , REZAZADEGAN TAVAKOLI, Hamed , LE, Nam, Hai , GHAZNAVI YOUVALARI, Ramin , AHONEN, Jukka, Ilari , AKSU, Emre, Baris
IPC分类号： H04N19/117 , H04N19/85 , G06N3/04 , G06N3/08 , G06V10/20 , G06T9/00
摘要： The embodiments relate to a method for encoding and decoding, and a technical equipment for implementing the methods. The method for encoding comprises receiving input media data; preprocessing the input media data by one or more pre-processing filters (1010); compressing the preprocessed input media data by a video codec (1020); and including information characterizing the one or more pre-processing filters (1010) in or along the compressed media data.

5. 发明申请

WO2022084762A1 APPARATUS, METHOD AND COMPUTER PROGRAM PRODUCT FOR LEARNED VIDEO CODING FOR MACHINE 审中-公开
公开(公告)号：WO2022084762A1
公开(公告)日：2022-04-28
申请号：PCT/IB2021/058036
申请日：2021-09-02
申请人： NOKIA TECHNOLOGIES OY
发明人： LE, Nam , CRICRÌ, Francesco , ZHANG, Honglei , REZAZADEGAN TAVAKOLI, Hamed , GHAZNAVI YOUVALARI, Ramin
IPC分类号： G06T9/00 , H04N19/136
摘要： A method is provided for computing predetermined loss terms based on original data and decoded data; training one or more neural networks of a system by using the predetermined loss terms; updating weights for one or more of other loss terms; anddetermining trade-offs between predetermined objectives of the system. Corresponding apparatuses and computer program products are also provided.

6. 发明申请

WO2019211514A1 VIDEO ENCODING AND DECODING 审中-公开
公开(公告)号：WO2019211514A1
公开(公告)日：2019-11-07
申请号：PCT/FI2019/050317
申请日：2019-04-18
申请人： NOKIA TECHNOLOGIES OY
发明人： GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/59 , H04N19/597 , G06T3/00 , H04N19/58
摘要： There are disclosed various methods, apparatuses and computer program products for video encoding and decoding. In some embodiments, a block of samples of an image is obtained for motion prediction (1402). A model for scaling or refining is derived on the basis of a projection format of the image (1400). A location and a size of the block of samples (1404) and a motion vector, size and location of a reference block of the block of samples (1406) are obtained. The obtained information of the reference block and the block of samples is used for determining a modifying factor (1408), wherein at least the motion vector of the reference block is modified by using the modifying factor (1410).

7. 发明申请

WO2017158236A2 A METHOD, AN APPARATUS AND A COMPUTER PROGRAM PRODUCT FOR CODING A 360-DEGREE PANORAMIC IMAGES AND VIDEO 审中-公开
标题翻译：用于编码360度全景图像和视频的方法，设备和计算机程序产品
公开(公告)号：WO2017158236A2
公开(公告)日：2017-09-21
申请号：PCT/FI2017/050167
申请日：2017-03-14
申请人： NOKIA TECHNOLOGIES OY
发明人： HANNUKSELA, Miska , AMINLOU, Alireza , GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/132
CPC分类号： G06T9/00 , H04N19/132 , H04N19/167 , H04N19/176 , H04N19/182 , H04N19/88
摘要： A method and an apparatus for encoding and decoding 360-degree panoramic images and video. A non-rectangular effective picture area representing 360-degree panorama picture is determined; a mapped 360-degree panorama picture covering the effective picture area is obtained; a non-rectangular and at least partially block-aligned reshaped picture from the mapped 360-degree panorama picture is obtained using a first processing. The first processing comprises identifying a boundary block containing a boundary of the effective picture area; removing zero or more samples of the boundary block; setting sample values of samples in the boundary block and outside the effective picture area by copying sample values from an opposite-side boundary region of the effective picture area and/or moving samples from an opposite-side boundary region of the effective picture area; and using a second processing to the reshaped picture to obtain a rectangular picture and encoding the rectangular picture into a bitstream.
摘要翻译：用于编码和解码360度全景图像和视频的方法和设备。表示360度全景图像的非矩形有效图像区域被确定; 获得覆盖有效图像区域的映射的360度全景图像; 使用第一处理获得来自映射的360度全景图片的非矩形且至少部分块对齐的重塑图片。第一处理包括识别包含有效图像区域的边界的边界块; 去除边界块的零个或多个样本; 通过从有效图像区域的相反侧边界区域复制样本值和/或从有效图像区域的相反侧边界区域移动样本，设置边界块内和有效图像区域外的样本的样本值; 以及对整形后的图片进行第二次处理以获得矩形图片并将矩形图片编码成比特流。

8. 发明申请

WO2023066672A1 VIDEO CODING USING PARALLEL UNITS 审中-公开
公开(公告)号：WO2023066672A1
公开(公告)日：2023-04-27
申请号：PCT/EP2022/077796
申请日：2022-10-06
申请人： NOKIA TECHNOLOGIES OY
发明人： LAINEMA, Jani , GHAZNAVI YOUVALARI, Ramin , AMINLOU, Alireza , ASTOLA, Pekka , ZARE, Alireza , HANNUKSELA, Miska Matias , HONG, Seungwook , WANG, Limin , PANUSOPONE, Krit
IPC分类号： H04N19/436 , H04N19/59 , H04N19/593 , H04N19/523
摘要： An apparatus includes circuitry configured to: determine a block of samples in a picture; determine a parallel unit the block belongs to; determine at least one row of reference samples not belonging to the parallel unit, wherein the row is not dependent from decoded samples of any parallel unit within the picture; determine a location of at least one reference sample; and in response to the location of the at least one reference sample belonging to the parallel unit the block of samples belongs to, determine a value for the reference sample from decoded samples of the parallel unit the block of samples belongs to; or in response to the location of the reference sample being at a location not belonging to the parallel unit, determine a value for the reference sample from the row of reference samples coded independently from reconstructed samples of any parallel unit within the picture.

9. 发明申请

WO2020234512A2 A METHOD, AN APPARATUS AND A COMPUTER PROGRAM PRODUCT FOR VIDEO ENCODING AND VIDEO DECODING 审中-公开
公开(公告)号：WO2020234512A2
公开(公告)日：2020-11-26
申请号：PCT/FI2020/050327
申请日：2020-05-15
申请人： NOKIA TECHNOLOGIES OY
发明人： GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/593 , H04N19/105 , H04N19/119 , H04N19/136 , H04N19/176 , H04N19/11 , G06T9/00 , H04N19/159 , H04N19/423
摘要： The embodiments relate to a method and technical equipment, wherein the method comprises receiving a source picture; partitioning the source picture into a set of non-overlapping blocks; for a block, obtaining at least one sample/pixel value and its location from at least one neighboring block; deriving a prediction model for the block that relates the sample(s) of neighboring block(s) to the corresponding location(s) of the neighboring block(s); predicting a sample value of the sample of a first prediction area based on the derived prediction model and the sample location inside the first prediction area; deriving at least one other prediction model for at least one other prediction area using the predicted samples and their locations from the prediction area being previously predicted; and predicting a sample value of the sample of the at least one other prediction area based on said at least one other prediction model and the sample location inside said at least one other prediction area.

10. 发明申请

WO2019073113A1 AN APPARATUS, A METHOD AND A COMPUTER PROGRAM FOR VIDEO CODING AND DECODING 审中-公开
公开(公告)号：WO2019073113A1
公开(公告)日：2019-04-18
申请号：PCT/FI2018/050713
申请日：2018-10-04
申请人： NOKIA TECHNOLOGIES OY
发明人： AMINLOU, Alireza , HANNUKSELA, Miska , GHAZNAVI YOUVALARI, Ramin
IPC分类号： H04N19/593 , H04N19/55 , H04N19/17 , H04N19/167 , H04N19/33 , H04N21/2343 , H04N21/4728
CPC分类号： H04N19/167 , H04N19/17 , H04N19/33 , H04N19/55 , H04N19/593 , H04N21/2343 , H04N21/4728
摘要： A method comprising: encoding an input picture sequence into a first bitstream, said encoding comprising: assigning a picture area to a first constituent picture area and a first tile area that are non-overlapping within the picture area; encoding a first input picture into a coded constituent picture of a first coded picture of the first bitstream, wherein the coded constituent picture in the first bitstream occupies the first constituent picture area, and the first coded picture of the first bitstream occupies the picture area, and wherein said encoding comprises reconstructing a first reconstructed constituent picture corresponding to the coded constituent picture in the first bitstream; and encoding a first region of the first input picture into a first set of coded tiles, wherein the first set of coded tiles occupies the first tile area, and wherein said encoding comprises prediction using the coded constituent picture in the first bitstream or the first reconstructed constituent picture as a reference, and the first set of coded tiles is encoded into the first coded picture or into a second coded picture of the first bitstream, the second coded picture occupying the picture area.

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