-
公开(公告)号：US11979175B2
公开(公告)日：2024-05-07
申请号：US17941318
申请日：2022-09-09
发明人： Yoo Jin Choi , Mostafa El-Khamy , Jungwon Lee
CPC分类号： H03M7/6011 , G06N3/04 , G06N3/08 , H04L1/0003 , H04L1/0009 , H04N19/13 , H04N19/147 , H04N19/19
摘要： A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method for compression includes receiving a first image and a first scheme as inputs for an autoencoder network; determining a first Lagrange multiplier based on the first scheme; and using the first image and the first Lagrange multiplier as inputs, computing a second image from the autoencoder network. The autoencoder network is trained using a plurality of Lagrange multipliers and a second image as training inputs.
-
2.发明授权公开(公告)号：US11889081B2
公开(公告)日：2024-01-30
申请号：US17890583
申请日：2022-08-18
申请人： ORANGE
发明人： Felix Henry , Mohsen Abdoli
IPC分类号： H04N19/124 , H04N19/11 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/593 , H04N19/61
CPC分类号： H04N19/124 , H04N19/11 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/593 , H04N19/61
摘要： A coding method and a decoding method for decoding a coded data stream representative of at least one image that is split into blocks. For at least one current block of the image, an item of information indicating a coding mode of the current block is decoded from the data stream. When the coding mode of the current block corresponds to a first coding mode, the current block is decoded using a first determined quantization step to dequantize, in the transform domain, a prediction residue associated with the current block. When the coding mode of the current block corresponds to a second coding mode, the current block is decoded using a second determined quantization step to dequantize, in the spatial domain, a prediction residue associated with the current block. The first quantization step and the second quantization step are determined according to the same quantization parameter.
-
3.发明授权公开(公告)号：US11863751B2
公开(公告)日：2024-01-02
申请号：US17890598
申请日：2022-08-18
申请人： ORANGE
发明人： Felix Henry , Mohsen Abdoli
IPC分类号： H04N19/124 , H04N19/11 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/593 , H04N19/61
CPC分类号： H04N19/124 , H04N19/11 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/593 , H04N19/61
摘要： A coding method and a decoding method for decoding a coded data stream representative of at least one image that is split into blocks. For at least one current block of the image, an item of information indicating a coding mode of the current block is decoded from the data stream. When the coding mode of the current block corresponds to a first coding mode, the current block is decoded using a first determined quantization step to dequantize, in the transform domain, a prediction residue associated with the current block. When the coding mode of the current block corresponds to a second coding mode, the current block is decoded using a second determined quantization step to dequantize, in the spatial domain, a prediction residue associated with the current block. The first quantization step and the second quantization step are determined according to the same quantization parameter.
-
公开(公告)号：US20190037246A1
公开(公告)日：2019-01-31
申请号：US16150507
申请日：2018-10-03
申请人： Sun Patent Trust
发明人： Hisao SASAI , Takahiro NISHI , Youji SHIBAHARA , Toshiyasu SUGIO
IPC分类号： H04N19/96 , H04N19/61 , H04N19/147 , H04N19/463 , H04N19/19 , H04N19/119 , H04N19/70 , H04N19/124 , H04N19/17 , H04N19/182
CPC分类号： H04N19/96 , H04N19/119 , H04N19/124 , H04N19/147 , H04N19/17 , H04N19/182 , H04N19/19 , H04N19/463 , H04N19/61 , H04N19/70
摘要： Provided is an image coding method that partitions an input image signal into processing units, and that codes the partitioned image to generate a code sequence. In particular, the image coding method determines a partitioning pattern for hierarchically partitioning the input image signal in order starting from a largest unit of the processing units, generates partition information indicative of the partitioning pattern, and codes partition information. The partition information includes maximum used hierarchy depth information indicative of a maximum used hierarchy depth which is a hierarchy depth of a deepest processing unit of the processing units included in the partitioning pattern.
-
公开(公告)号：US10038900B2
公开(公告)日：2018-07-31
申请号：US15477637
申请日：2017-04-03
申请人： SK TELECOM CO., LTD.
发明人： Jeongyeon Lim , Joong Gunn Park , Yunglyul Lee , Joohee Moon , Haekwang Kim , Byeungwoo Jeon , Jongki Han , Ryeonghee Kwon
IPC分类号： H04N19/103 , H04N19/157 , H04N19/52 , H04N19/61 , H04N5/14 , H04N19/70 , H04N19/119 , H04N19/105
CPC分类号： H04N19/103 , G06T9/004 , H04N1/417 , H04N5/145 , H04N19/119 , H04N19/147 , H04N19/157 , H04N19/176 , H04N19/19 , H04N19/513 , H04N19/52 , H04N19/61 , H04N19/70 , H04N19/96
摘要： An apparatus for encoding images includes: a predictor to determine a prediction unit (PU) mode among a plurality of PU modes indicating types of partition of a current coding unit (CU) into one or more prediction units (PUs), and generate a predicted block of the current CU by performing an intra prediction or an inter prediction for each PU of the determined PU mode, wherein a size of the current CU is 2N×N, and the plurality of PU modes includes 2N×hN or hN×N PU mode in which the current CU is partitioned into PUs respectively having a size of 2N×hN or hN×N, h being a fractional number smaller than 1; a subtractor to subtract the predicted block from the current CU to generate a residual block; a transformer to transform the residual block into a frequency domain to generate a frequency one or more transform blocks.
-
公开(公告)号：US09998739B2
公开(公告)日：2018-06-12
申请号：US15060273
申请日：2016-03-03
发明人： Jaehong Chon , In Suk Chong , Wei-Jung Chien , Xianglin Wang , Marta Karczewicz
IPC分类号： H04N7/12 , G06K9/46 , H04N19/139 , H04N19/119 , H04N19/176 , H04N19/147 , H04N19/513 , H04N19/107 , H04N19/61 , H04N19/103 , H04N19/19
CPC分类号： H04N19/139 , H04N19/103 , H04N19/107 , H04N19/119 , H04N19/147 , H04N19/176 , H04N19/19 , H04N19/513 , H04N19/61
摘要： To encode video data, a video encoder partitions a 2N×2N block of video data into four N×N blocks, determines encoding modes for each of the four N×N blocks, calculates values representative of encoded versions of the four N×N blocks using the encoding modes for each of the four N×N blocks, determines whether to skip testing of at least one non-square partitioning mode for the 2N×2N block based on the calculated values, and encodes the 2N×2N block based at least in part on the determination of whether to skip testing of the at least one non-square partitioning mode.
-
7.发明申请公开(公告)号：US20180139430A1
公开(公告)日：2018-05-17
申请号：US15856506
申请日：2017-12-28
发明人： Dae-sung CHO , Hyun-mun KIM , Woo-shik KIM , Dmitri Birinov
IPC分类号： H04N11/04 , H04N11/02 , H04N19/109 , H04N19/80 , H04N19/70 , H04N19/61 , H04N19/593 , H04N19/50 , H04N19/463 , H04N19/46 , H04N19/44 , H04N19/196 , H04N19/19 , H04N19/186 , H04N19/182 , H04N19/18 , H04N19/176 , H04N19/147 , H04N19/136 , H04N19/132 , H04N19/11 , H04N19/91
CPC分类号： H04N11/042 , H04N11/02 , H04N19/109 , H04N19/11 , H04N19/132 , H04N19/136 , H04N19/147 , H04N19/176 , H04N19/18 , H04N19/182 , H04N19/186 , H04N19/19 , H04N19/196 , H04N19/44 , H04N19/46 , H04N19/463 , H04N19/50 , H04N19/593 , H04N19/61 , H04N19/70 , H04N19/80 , H04N19/91
摘要： A method, medium, and apparatus encoding and/or decoding an image in order to increase encoding and decoding efficiency by performing binary-arithmetic coding/decoding on a binary value of a syntax element using a probability model having the same syntax element probability value for respective context index information of each of at least two image components.
-
公开(公告)号：US20180109702A1
公开(公告)日：2018-04-19
申请号：US15686598
申请日：2017-08-25
发明人： Sang-kwon NA , Doo-hyun KIM , Ki-won YOO
IPC分类号： H04N1/64 , H04N19/36 , H04N19/124 , H04N19/176 , H04N19/186 , H04N19/19
CPC分类号： H04N1/646 , H04N1/6058 , H04N19/124 , H04N19/176 , H04N19/186 , H04N19/19 , H04N19/36 , H04N19/85
摘要： An image processing apparatus is provided. The image processing apparatus includes a signal processor and a controller. The signal processor processes an image signal including a plurality of color components. The controller controls the signal processor to perform a color gamut conversion, a domain transform, a quantization processing and an encoding processing with respect to an input image signal, and in response to differences between the color components of the image signal being less than a first critical level, to not perform the color gamut conversion.
-
公开(公告)号：USRE46777E1
公开(公告)日：2018-04-03
申请号：US15013843
申请日：2016-02-02
IPC分类号： H04N7/18 , H04N19/19 , H04N19/46 , H04N19/129 , H04N19/12 , H04N19/126 , H04N19/14 , H04N19/147 , H04N19/61
CPC分类号： H04N19/19 , H04N19/12 , H04N19/126 , H04N19/129 , H04N19/14 , H04N19/147 , H04N19/46 , H04N19/61
摘要： Method for coding a video signal using hybrid coding, comprising: reducing temporal redundancy by block based motion compensated prediction in order to establish a prediction error signal; performing quantization on samples of the prediction error signal or on coefficients resulting from a transformation of the prediction error signal into the frequency domain to obtain quantized values, representing quantized samples or quantized coefficients respectively; calculating a quantization efficiency for the quantized values; calculating a zero efficiency for a quantization, when the quantized values are set to zero; selecting the higher efficiency; and maintaining the quantized values or setting quantized values to zero, for further proceeding, depending on the selected efficiency.
-
公开(公告)号：US09813702B2
公开(公告)日：2017-11-07
申请号：US14518558
申请日：2014-10-20
发明人： Byeong Moon Jeon , Seung Wook Park , Joon Young Park , Jae Won Sung , Hyun Wook Park , Jee Hong Lee , Jin Young Lee , Dong San Jun , Yinji Piao
IPC分类号： H04N19/19 , H04N19/80 , H04N19/70 , H04N19/55 , H04N19/51 , G06F1/00 , G06K9/00 , H04N19/00 , H04N19/56 , H04N19/52 , H04N19/139 , H04N19/176 , H04N19/147 , H04N19/513 , H04N19/593 , H04N19/11 , H04N19/132 , H04N19/182
CPC分类号： H04N19/55 , G06F1/00 , G06K9/00 , H04N19/00 , H04N19/11 , H04N19/132 , H04N19/139 , H04N19/147 , H04N19/176 , H04N19/182 , H04N19/19 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/56 , H04N19/593 , H04N19/70 , H04N19/80
摘要： The present invention is directed to a method and apparatus for decoding a bitstream for a video signal. More specifically, the present invention is directed to a method comprising determining a motion vector candidate set of a current block; obtaining motion vector indication information of the current block from the bitstream; determining a motion vector indicated by the obtained motion vector indication information from the motion vector candidate set of the current block as a predicted motion vector of the current block; and performing motion compensation on the current block based on the predicted motion vector, and an apparatus therefor.
-
-
-
-
-
-
-
-
-
搜索结果
1040 条记录 (耗时 0.034 秒)
