-
1.
公开(公告)号:US20240348788A1
公开(公告)日:2024-10-17
申请号:US18628969
申请日:2024-04-08
Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE , INDUSTRY-ACADEMIA COOPERATION GROUP OF SEJONG UNIVERSITY
Inventor: Woong LIM , Jin-Young Lee , Gun Bang , Hui-Yong Kim
IPC: H04N19/137 , H04N19/159 , H04N19/176 , H04N19/182
CPC classification number: H04N19/137 , H04N19/159 , H04N19/176 , H04N19/182
Abstract: Disclosed herein are a method, an apparatus, and a storage medium for image encoding/decoding using geometric partitioning. A target block may be geometrically partitioned, and multiple partitioned regions may be generated from geometric partitioning. Each partitioned region may have a non-square and a non-rectangular shape. Different prediction schemes may be applied to different partitioned regions. The different prediction schemes for multiple partitioned regions may be signaled as explicit information, and may be derived using information about a coding parameter for the target block or the like.
-
公开(公告)号:US20240348775A1
公开(公告)日:2024-10-17
申请号:US18756664
申请日:2024-06-27
Inventor: Tadamasa TOMA , Takahiro NISHI , Kiyofumi ABE , Yusuke KATO
IPC: H04N19/105 , H04N19/176 , H04N19/182
CPC classification number: H04N19/105 , H04N19/176 , H04N19/182
Abstract: An encoder includes circuitry and memory connected to the circuitry. The circuitry, in operation: derives, as a first parameter, a total sum of absolute values of sums of horizontal gradient values respectively for pairs of relative pixel positions; derives, as a second parameter, a total sum of absolute values of sums of vertical gradient values respectively for the pairs of relative pixel positions; derives, as a third parameter, a total sum of horizontal-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fourth parameter, a total sum of vertical-related pixel difference values respectively for the pairs of relative pixel positions; derives, as a fifth parameter, a total sum of vertical-related sums of horizontal gradient values respectively for the pairs of relative pixel positions; and generates a prediction image to be used to encode the current block using the first, second, third, fourth, and fifth parameters.
-
公开(公告)号:US20240340411A1
公开(公告)日:2024-10-10
申请号:US18293375
申请日:2022-03-07
Applicant: SONY SEMICONDUCTOR SOLUTIONS CORPORATION
Inventor: TAKEFUMI NAGUMO , TAKUYA KITAMURA
IPC: H04N19/11 , H04N19/124 , H04N19/182
CPC classification number: H04N19/11 , H04N19/124 , H04N19/182
Abstract: The present disclosure relates to an image processing device and method capable of suppressing a drop in encoding efficiency. One of spatial prediction and phase prediction is set as a prediction method for a pixel to be processed in image data generated by a pixel array in which blocks, each including a plurality of pixels adjacent to each other, are arranged in a predetermined pattern. A prediction value for the pixel to be processed is then derived by applying the prediction method set, and a prediction residual obtained by subtracting the prediction value from each of pixel values in the image data is encoded. The present disclosure can be applied in, for example, an image processing device, an encoding device, a decoding device, an electronic device, an image processing method, a program, or the like.
-
公开(公告)号:US12114003B2
公开(公告)日:2024-10-08
申请号:US18321829
申请日:2023-05-23
Applicant: Shrinivas Kudekar
Inventor: Shrinivas Kudekar , Ivan Klimek
IPC: H04N19/467 , H04N9/64 , H04N19/136 , H04N19/172 , H04N19/182 , H04N19/184 , H04N19/186 , H04N19/85 , G06K19/06 , G06Q30/0251
CPC classification number: H04N19/467 , H04N9/64 , H04N19/136 , H04N19/172 , H04N19/182 , H04N19/184 , H04N19/186 , H04N19/85 , G06K19/06028 , G06Q30/0261
Abstract: A system and method for managing encoded information in a real-time screen-to-camera communication environment are disclosed. The system converts information into a pre-defined number of characters and generates data symbols in shapes and pilot symbols corresponding to the characters. Further, the system embeds the data symbols in media content frames and modulates pixels and boundaries for display of display device, based on luminance, and adaptively displays frames as temporal-complementary frames. Furthermore, the system detects frames from recorded content, extracts data symbols based on grid and fixed pattern, and detects bit values by analyzing color differences. Additionally, the system generates information based on the detected bit values and outputs the information on an user device display, including products, recommendations, services, and relevant information related to the media content.
-
公开(公告)号:US20240333958A1
公开(公告)日:2024-10-03
申请号:US18616881
申请日:2024-03-26
Applicant: Alibaba (China) Co., Ltd.
Inventor: Shuqing Fang , Jianhua Chen , Yan YE
IPC: H04N19/51 , H04N19/105 , H04N19/176 , H04N19/182
CPC classification number: H04N19/51 , H04N19/105 , H04N19/176 , H04N19/182
Abstract: A motion compensation method, includes acquiring a motion vector of an initial search point in a reference frame of an adjacent block to a to-be-processed block in a to-be-processed image and a motion vector of the adjacent block; determining a search range in the reference frame based on the motion vector of the initial search point and the motion vector of the adjacent block; determining a target pixel in the search range; and performing motion compensation on the to-be-processed block based on the motion vector of the target pixel.
-
公开(公告)号:US12108039B2
公开(公告)日:2024-10-01
申请号:US18451694
申请日:2023-08-17
Inventor: Ryuichi Kanoh , Takahiro Nishi , Tadamasa Toma
IPC: H04N19/117 , H04N19/176 , H04N19/182 , H04N19/186
CPC classification number: H04N19/117 , H04N19/176 , H04N19/182 , H04N19/186
Abstract: An encoding method includes: changing values of luma pixels in a first block and a second block to filter a first boundary between the first block and the second block, using clipping such that change amounts of the respective values are within respective luma clip widths, the luma pixels in the first block and the second block being arranged along a first line across the first boundary; and changing values of chroma pixels in a third block and a fourth block to filter a second boundary between the third block and the fourth block, using clipping such that change amounts of the respective values are within respective chroma clip widths, the chroma pixels in the third block and the fourth block being arranged along a second line across the second boundary. The luma clip widths applied to the luma pixels are selected to be asymmetrical relative to the first boundary.
-
公开(公告)号:US20240323415A1
公开(公告)日:2024-09-26
申请号:US18188070
申请日:2023-03-22
Applicant: QUALCOMM Incorporated
Inventor: David Wilson ROMERO GUZMAN , Gabriele CESA , Guillaume Konrad SAUTIERE , Yunfan ZHANG , Taco Sebastiaan COHEN , Auke Joris WIGGERS
IPC: H04N19/42 , G06T3/40 , H04N19/182
CPC classification number: H04N19/42 , G06T3/4046 , H04N19/182
Abstract: Certain aspects of the present disclosure provide techniques and apparatus for encoding content using a neural network. An example method generally includes encoding video content into a latent space representation through an encoder implemented by a first machine learning model. A code is generated by upsampling the latent space representation of the video content. A prior is calculated based on a conditional probability of obtaining the upsampled latent space representation conditioned by the latent space representation of the video content. A compressed version of the video content is generated based on a probabilistic model implemented by a second machine learning model, the generated code, and the calculated prior, and the compressed version of the video content is output for transmission.
-
公开(公告)号:US12101500B2
公开(公告)日:2024-09-24
申请号:US18381949
申请日:2023-10-19
Applicant: ARRIS Enterprises LLC
Inventor: Krit Panusopone , Yue Yu , Seungwook Hong , Limin Wang
IPC: H04N19/50 , H04N19/105 , H04N19/107 , H04N19/11 , H04N19/136 , H04N19/176 , H04N19/182 , H04N19/186 , H04N19/52 , H04N19/59 , H04N19/593 , H04N19/82 , H04N19/96 , H04N19/119 , H04N19/126
CPC classification number: H04N19/50 , H04N19/105 , H04N19/107 , H04N19/11 , H04N19/136 , H04N19/176 , H04N19/182 , H04N19/186 , H04N19/52 , H04N19/59 , H04N19/593 , H04N19/82 , H04N19/96 , H04N19/119 , H04N19/126
Abstract: A method of decoding JVET video includes receiving a bitstream and calculating a final planar prediction in planar mode to predict pixel values for a current coding block. The final planar prediction may rely on using unequal weights applied to each of a horizontal and vertical predictor, where such predictors may be generated by interpolating neighboring pixels for each predicted pixel within a coding block. The computation may be made more accurate by deriving a value for a bottom right neighboring pixel.
-
公开(公告)号:US12101469B2
公开(公告)日:2024-09-24
申请号:US18193738
申请日:2023-03-31
Applicant: B1 INSTITUTE OF IMAGE TECHNOLOGY, INC.
Inventor: Ki Baek Kim
IPC: H04N19/117 , H04N19/105 , H04N19/159 , H04N19/176 , H04N19/182
CPC classification number: H04N19/105 , H04N19/117 , H04N19/159 , H04N19/176 , H04N19/182
Abstract: A method and apparatus for encoding/decoding images according to the present invention may configure a prediction mode candidate group on a screen of a target block, determine a reference pixel for a prediction mode on the screen of the target block, perform at least one of filtering and interpolation on the reference pixel, and perform prediction on the screen of the target block on the basis of the prediction mode candidate group on the screen and the reference pixel.
-
10.
公开(公告)号:US20240314292A1
公开(公告)日:2024-09-19
申请号:US18673163
申请日:2024-05-23
Inventor: Tao ZHANG
IPC: H04N19/103 , H04N19/119 , H04N19/157 , H04N19/172 , H04N19/182 , H04N19/186
CPC classification number: H04N19/103 , H04N19/119 , H04N19/157 , H04N19/172 , H04N19/182 , H04N19/186
Abstract: A video coding method is performed by a computing device, and the method includes: dividing a to-be-coded video frame image into a plurality of coding units; and for each coding unit, performing the following operations: determining color composition of the coding unit, the color composition comprising a quantity of colors comprised in the coding unit, further comprising: clustering a color of each pixel in the coding unit, to determine a type of the color comprised in the coding unit; and generating a color index table based on the type of the color comprised in the coding unit, wherein a quantity of color indexes comprised in the color index table corresponds to the quantity of colors; and in response to that the quantity of colors is less than or equal to a preset color quantity threshold, determining a coding mode of the coding unit to be a palette coding mode.
-
-
-
-
-
-
-
-
-