公开(公告)号：US20230388483A1

公开(公告)日：2023-11-30

申请号：US17751754

申请日：2022-05-24

Applicant: OP Solutions LLC

Inventor： Hari Kalva ,  Borivoje Furht ,  Velibor Adzic

IPC: H04N19/105 ,  H04N19/172 ,  H04N19/139 ,  H04N19/80

CPC classification number: H04N19/105 ,  H04N19/172 ,  H04N19/139 ,  H04N19/80

Abstract: A decoder includes circuitry configured to receive a bitstream, identify a first frame, locate a first independent reference region within the first frame, extract the first independent reference region from the first frame, decode a second frame using the first independent reference region as a reference for the second frame.

公开(公告)号：US20230370582A1

公开(公告)日：2023-11-16

申请号：US18225205

申请日：2023-07-24

Applicant: LX Semicon Co., Ltd.

Inventor： Jin Ho LEE ,  Hyun Suk KO ,  Jung Won KANG ,  Sung Chang LIM ,  Ha Hyun LEE ,  Dong San JUN ,  Seung Hyun CHO ,  Hui Yong KIM ,  Jin Soo CHOI

IPC: H04N19/105 ,  H04N19/176 ,  H04N19/11 ,  H04N19/119 ,  H04N19/186 ,  H04N19/80 ,  H04N19/91 ,  H04N19/593 ,  H04N19/117 ,  H04N19/51 ,  H04N19/159 ,  H04N19/70 ,  H04N19/96 ,  H04N19/172

CPC classification number: H04N19/105 ,  H04N19/176 ,  H04N19/11 ,  H04N19/119 ,  H04N19/186 ,  H04N19/80 ,  H04N19/91 ,  H04N19/593 ,  H04N19/117 ,  H04N19/51 ,  H04N19/159 ,  H04N19/70 ,  H04N19/96 ,  H04N19/172

Abstract: An image encoding/decoding method and apparatus for predicting a second color component block using a first color component block are provided. An image decoding method of the present invention comprises deriving a prediction parameter using the first color component block, and predicting the second color component block using the derived prediction parameter.

公开(公告)号：US20230353766A1

公开(公告)日：2023-11-02

申请号：US18338143

申请日：2023-06-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Elena Alexandrovna Alshina ,  Han Gao ,  Semih Esenlik

IPC: H04N19/42 ,  H04N19/132 ,  H04N19/463 ,  H04N19/80 ,  H04N19/187 ,  H04N19/172 ,  H04N19/85

CPC classification number: H04N19/42 ,  H04N19/132 ,  H04N19/463 ,  H04N19/80 ,  H04N19/187 ,  H04N19/172 ,  H04N19/85

Abstract: A method and an apparatus for encoding a picture and decoding a bitstream representing a matrix using a neural network is provided. The method includes obtaining a resizing method out of a plurality of resizing methods. The resizing method is applied to resize an input of size S to a size S. The resized input is processed by the neural network, wherein the neural network comprises one or more downsampling layers. Subsequently, the method provides an output of the neural network, the output having a size P that is smaller than S in the at least one dimension

公开(公告)号：US20230353733A1

公开(公告)日：2023-11-02

申请号：US18206499

申请日：2023-06-06

Applicant: LG Electronics Inc.

Inventor： Hyeong Moon JANG ,  Sangheon LEE

IPC: H04N19/117 ,  H04N19/186 ,  H04N19/132 ,  H04N19/46 ,  H04N19/80

CPC classification number: H04N19/117 ,  H04N19/132 ,  H04N19/186 ,  H04N19/46 ,  H04N19/80

Abstract: An image encoding/decoding method and apparatus are provided. An image decoding method according to the present disclosure may comprise obtaining a reconstructed picture, determining a target boundary of deblocking filtering in the reconstructed picture, determining a boundary strength for the target boundary, and applying deblocking filtering to the target boundary based on the boundary strength. Based on the target boundary being a transform block boundary and a color component of the reconstructed picture being a chroma component, the boundary strength may be determined based on whether joint CbCr residual coding is performed on at least one of two blocks adjacent to the target boundary, and the joint CbCr residual coding may correspond to encoding residual samples for a chroma Cb component and a chroma Cr component as a single transform block.

公开(公告)号：US20230336789A1

公开(公告)日：2023-10-19

申请号：US18302631

申请日：2023-04-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Kwan Jung OH ,  Gwang Soon LEE ,  Hong Chang SHIN ,  Jun Young JEONG ,  Jeong Il SEO ,  Jae Gon KIM ,  Sung Gyun LIM ,  Hyeon Jong HWANG

IPC: H04N19/85 ,  H04N19/176 ,  H04N19/136 ,  H04N19/80

CPC classification number: H04N19/85 ,  H04N19/176 ,  H04N19/136 ,  H04N19/80

Abstract: An immersive image encoding method according to the present disclosure includes classifying a plurality of view images into a basic image and an additional image; performing pruning for at least one of the plurality of view images based on the classification result; generating a depth atlas based on a result of performing the pruning; and correcting an occupancy state of pixels in the depth atlas.

公开(公告)号：US20230328292A1

公开(公告)日：2023-10-12

申请号：US18132640

申请日：2023-04-10

Applicant: Sharp Kabushiki Kaisha

Inventor： Takeshi CHUJOH ,  Tomohiro IKAI ,  Yukinobu YASUGI ,  Yasuaki TOKUMO ,  Tomonori HASHIMOTO ,  Tomoko AONO ,  Keiichiro TAKADA

IPC: H04N19/80 ,  H04N19/85 ,  H04N19/172

CPC classification number: H04N19/80 ,  H04N19/85 ,  H04N19/172

Abstract: Object
There is the problem in the related art that the relationship between a patch size which is a unit of processing of a neural network and the sizes of input and output pictures is not clearly defined.
Solution
A video decoding apparatus for generating a decoded picture by decoding coded data, the video decoding apparatus comprising:



resolution inverse conversion circuit that performs a post-filtering by using a neural network specified by resolution conversion information; and
neural network filter circuit that derives:
(i) first information relating to a size of a picture,
(ii) second information specifying a size of a picture resulting from applying the post-filtering,
(iii) third information indicating a patch size for the post-filtering, and
(iv) fourth information for output patch derived by using the third information,
wherein
a product of a value of the first information and a value of the fourth information is equal to a product of a value of the second information and a value of the third information.

公开(公告)号：US20230300356A1

公开(公告)日：2023-09-21

申请号：US18110226

申请日：2023-02-15

Applicant: ATEME

Inventor： Thomas Guionnet ,  Marwa Tarchouli

IPC: H04N19/42 ,  H04N19/119 ,  H04N19/176 ,  H04N19/80 ,  H04N19/147 ,  G06N20/00

CPC classification number: H04N19/42 ,  G06N20/00 ,  H04N19/119 ,  H04N19/147 ,  H04N19/176 ,  H04N19/80 ,  H04N19/593

Abstract: A method for encoding image data of an image divided into a plurality of pixel blocks using a machine learning algorithm, is proposed, which comprises, by a computing platform comprising a processor configured for implementing the machine learning algorithm, for a block of the pixel blocks: obtaining a block neighborhood set of at least one pixel of the image, wherein the at least one pixel is located outside the block in a spatial neighborhood of a corresponding pixel located on an edge of the pixel block, and generating, by the machine learning algorithm configured for performing end-to-end image compression, a bitstream representing the encoded pixel block, by encoding the pixel block based on input data comprising the pixel block and the block neighborhood set.

公开(公告)号：US20230300327A1

公开(公告)日：2023-09-21

申请号：US18142166

申请日：2023-05-02

Applicant: Panasonic Intellectual Property Corporation of America

Inventor： Chong Soon LIM ,  Hai Wei SUN ,  Han Boon TEO ,  Jing Ya LI ,  Che-Wei KUO ,  Kiyofumi ABE ,  Tadamasa TOMA ,  Takahiro NISHI ,  Yusuke KATO

IPC: H04N19/117 ,  H04N19/176 ,  H04N19/51 ,  H04N19/80

CPC classification number: H04N19/117 ,  H04N19/176 ,  H04N19/51 ,  H04N19/80

Abstract: An encoder that encodes a current block to be encoded in an image is provided. The encoder includes: processor; and memory coupled to the processor, in which, in operation, the processor: generates a first prediction image based on a motion vector, the first prediction image being an image with full-pel precision; generates a second prediction image using an interpolation filter by interpolating a value at a fractional-pel position between full-pel positions included in the first prediction image; and encodes the current block based on the second prediction image, and in the using of the interpolation filter, the interpolation filter is switched between a first interpolation filter and a second interpolation filter differing in a total number of taps from the first interpolation filter.

公开(公告)号：US11758149B2

公开(公告)日：2023-09-12

申请号：US17715903

申请日：2022-04-07

Applicant: LG Electronics Inc.

Inventor： Seung Wook Park ,  Jae Hyun Lim ,  Jung Sun Kim ,  Joon Young Park ,  Young Hee Choi ,  Byeong Moon Jeon ,  Yong Joon Jeon

IPC: H04N19/157 ,  H04N19/117 ,  H04N19/80 ,  H04N19/176 ,  H04N19/61 ,  H04N19/182 ,  H04N19/82

CPC classification number: H04N19/157 ,  H04N19/117 ,  H04N19/176 ,  H04N19/182 ,  H04N19/61 ,  H04N19/80 ,  H04N19/82

Abstract: According to the present invention, an image-encoding method comprises the following steps: receiving image information; generating a restored block for the current block based on the image information; and generating a finally restored block for the current block by applying an in-loop filter to the restored block on the basis of the image information. According to the present invention, image-encoding/decoding efficiency may be improved.

公开(公告)号：US20230276075A1

公开(公告)日：2023-08-31

申请号：US18313144

申请日：2023-05-05

Applicant: Beijing Bytedance Network Technology Co., Ltd. ,  Bytedance Inc.

Inventor： Kai Zhang ,  Li Zhang ,  Hongbin Liu ,  Yue Wang

IPC: H04N19/70 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/172 ,  H04N19/80 ,  H04N19/186 ,  H04N19/30 ,  H04N19/50 ,  H04N19/176

CPC classification number: H04N19/70 ,  H04N19/105 ,  H04N19/117 ,  H04N19/132 ,  H04N19/172 ,  H04N19/80 ,  H04N19/186 ,  H04N19/30 ,  H04N19/50 ,  H04N19/176

Abstract: A video processing method is provided, including: performing a conversion between a coded representation of a video including one or more video regions and the video, wherein the coded representation includes reshaping model information applicable for in-loop reshaping (ILR) of some of the one or more video regions, wherein the reshaping model information provides information for a reconstruction of a video unit of a video region based on a representation in a first domain and a second domain and/or scaling chroma residue of a chroma video unit, wherein the reshaping model information includes a parameter set that includes a first syntax element that derives a number of bits used to represent a second syntax element specifying an absolute delta codeword value from a corresponding bin, and wherein the first syntax element has a value smaller than a threshold.