公开(公告)号：US20240212179A1

公开(公告)日：2024-06-27

申请号：US18088206

申请日：2022-12-23

申请人： Rovi Guides, Inc.

发明人： Seppo Valli ,  Pekka Siltanen

IPC分类号： G06T7/50 ,  G06T15/04 ,  H04N19/136 ,  H04N19/184 ,  H04N19/436

CPC分类号： G06T7/50 ,  G06T15/04 ,  H04N19/136 ,  H04N19/184 ,  H04N19/436 ,  G06T2200/04 ,  G06T2207/10016

摘要： Systems and methods for encoding/decoding a 3D image are provided. The system accesses an image data that comprises a texture data and a depth map. The system decomposes the depth map into a plurality of component depth maps (CDMs) for a plurality of depth ranges, wherein each component depth map corresponds to a focal plane of multiple focal planes (MFPs) decomposition of the image data. The system generates a plurality of encoded CDM data streams for the plurality of depth ranges, wherein each respective CDM data stream is based at least in part on a respective CDM. The system then transmits the plurality of encoded CDM data streams to a client device to cause the client device to: (a) reconstruct the depth map, and (b) generate for display or for further processing an image based on the reconstructed depth map.

公开(公告)号：US20240205436A1

公开(公告)日：2024-06-20

申请号：US18426274

申请日：2024-01-29

申请人： BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.

发明人： Wei CHEN ,  Xiaoyu XIU ,  Yi-Wen CHEN ,  Hong-Jheng JHU ,  Che-Wei KUO ,  Xianglin WANG ,  Bing YU

IPC分类号： H04N19/436 ,  G06N3/0895 ,  H04N19/124 ,  H04N19/136 ,  H04N19/176 ,  H04N19/463

CPC分类号： H04N19/436 ,  G06N3/0895 ,  H04N19/124 ,  H04N19/136 ,  H04N19/463 ,  H04N19/176

摘要： A method and an apparatus for hybrid training of neural networks for video coding are provided. The method includes: obtaining, in an offline training stage, an offline trained network by training a neural network offline; and refining, in an online training stage, a plurality of neural network layers with constraint on a plurality of parameters of the plurality of neural network layers, where the plurality of neural network layers may include at least one neural network layer in the offline trained network or in a simple neural network connected to the offline trained network.

公开(公告)号：US20240196020A1

公开(公告)日：2024-06-13

申请号：US18585898

申请日：2024-02-23

申请人： Sun Patent Trust

发明人： Semih ESENLIK ,  Matthias NARROSCHKE ,  Thomas WEDI

IPC分类号： H04N19/70 ,  H04N19/174 ,  H04N19/30 ,  H04N19/423 ,  H04N19/436 ,  H04N19/46 ,  H04N19/52 ,  H04N19/597

CPC分类号： H04N19/70 ,  H04N19/174 ,  H04N19/30 ,  H04N19/423 ,  H04N19/436 ,  H04N19/46 ,  H04N19/52 ,  H04N19/597

摘要： A dependency indication is signaled within the beginning of a packet, that is, within the adjacent of a slice header to be parsed or a parameter set. This is achieved, for example, by including the dependency indication at the beginning of the slice header, preferably after a syntax element identifying the parameter set and before the slice address, by including the dependency indication before the slice address, by providing the dependency indication to a NALU header using a separate message, or by using a special NALU type for NALUs carrying dependent slices.

公开(公告)号：US20240187607A1

公开(公告)日：2024-06-06

申请号：US18414009

申请日：2024-01-16

申请人： Texas Instruments Incorporated

发明人： Minhua Zhou

IPC分类号： H04N19/167 ,  H04N19/103 ,  H04N19/117 ,  H04N19/12 ,  H04N19/124 ,  H04N19/157 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176 ,  H04N19/436 ,  H04N19/61 ,  H04N19/70 ,  H04N19/82

CPC分类号： H04N19/167 ,  H04N19/103 ,  H04N19/117 ,  H04N19/172 ,  H04N19/174 ,  H04N19/176 ,  H04N19/61 ,  H04N19/70 ,  H04N19/82 ,  H04N19/12 ,  H04N19/124 ,  H04N19/157 ,  H04N19/436

摘要： A method for coding a video sequence is provided that includes encoding a portion of a picture in the video sequence in lossless coding mode, and signaling a lossless coding indicator in a compressed bit stream, wherein the lossless coding indicator corresponds to the portion of a picture and indicates whether or not the portion of the picture is losslessly coded. A method for decoding a compressed video bit stream is provided that includes determining that lossless coding mode is enabled, decoding a lossless coding indicator from the compressed video bit stream, wherein the lossless coding indicator corresponds to a portion of a picture in the compressed video bit stream and indicates whether or not the portion of the picture is losslessly coded, and decoding the portion of the picture in lossless coding mode when the lossless coding indicator indicates the portion of the picture is losslessly coded.

公开(公告)号：US20240171762A1

公开(公告)日：2024-05-23

申请号：US17992153

申请日：2022-11-22

申请人： Argo AI, LLC

发明人： Florian Netter ,  Jonathan Michael Bonte ,  Kevin Nealis

IPC分类号： H04N19/423 ,  B60W60/00 ,  H04N19/136 ,  H04N19/436

CPC分类号： H04N19/423 ,  B60W60/001 ,  H04N19/136 ,  H04N19/436 ,  H04N9/64

摘要： Systems, methods, and computer-program products for video encoding for autonomous vehicles are disclosed. A method for video encoding for autonomous vehicles may include receiving image data associated with a plurality of images from at least one camera of an autonomous vehicle. The image data may be encoded into a plurality of video streams including at least one first video stream and at least one second video stream. The at least one first video stream may be associated with a first quality level. The at least one second video stream may be associated with a second quality level different than the first quality level. At least one of the plurality of video streams may be communicated to at least one data storage device.

公开(公告)号：US11985341B2

公开(公告)日：2024-05-14

申请号：US17847120

申请日：2022-06-22

申请人： ATI Technologies ULC

发明人： Wei Gao ,  Gabor Sines ,  Ihab M. A. Amer ,  Crystal Yeong-Pian Sau ,  Feng Pan ,  Dong Liu

IPC分类号： H04L65/70 ,  H04N19/14 ,  H04N19/146 ,  H04N19/172 ,  H04N19/176 ,  H04N19/436

CPC分类号： H04N19/436 ,  H04N19/14 ,  H04N19/146 ,  H04N19/172 ,  H04N19/176

摘要： A technique for encoding video is provided. The technique includes for a first portion of a first frame that is encoded by a first encoder in parallel with a second portion of the first frame that is encoded by a second encoder, determining a historical complexity distribution; determining a first bit budget for the first portion of the first frame based on the historical complexity distribution; and encoding the first portion of the first frame by the first encoder, based on the first bit budget.

公开(公告)号：US11968390B2

公开(公告)日：2024-04-23

申请号：US18052359

申请日：2022-11-03

申请人： CANON KABUSHIKI KAISHA

发明人： Guillaume Laroche

IPC分类号： H04N19/00 ,  H04N19/107 ,  H04N19/43 ,  H04N19/436 ,  H04N19/44 ,  H04N19/503 ,  H04N19/52 ,  H04N19/593

CPC分类号： H04N19/52 ,  H04N19/107 ,  H04N19/43 ,  H04N19/436 ,  H04N19/44 ,  H04N19/503 ,  H04N19/593

摘要： A method and device for deriving at least one motion information predictor for encoding of an image portion by motion compensation. At least two distinct first and second subsets of motion information predictors of a first set of motion information predictors are provided. Processing of the first subset of motion information predictors and processing of the second subset of motion information predictors is performed to obtain a final set of motion information predictors usable for predicting said image portion from the reference image portion. Processing of the second subset may comprise removing duplicates from among the motion information predictors of said second subset, and may be performed so as to exclude temporal predictors. At least part of the processing of the second subset of motion information predictors may be performed concurrently with at least part of the processing of the first subset of motion information predictors.

公开(公告)号：US20240129515A1

公开(公告)日：2024-04-18

申请号：US18240783

申请日：2023-08-31

申请人： Verily Life Sciences LLC

发明人： Joel Shor

IPC分类号： H04N19/50 ,  G06T7/73 ,  G06V10/774 ,  G06V10/82 ,  G06V20/40 ,  H04N19/136 ,  H04N19/147 ,  H04N19/184 ,  H04N19/436

CPC分类号： H04N19/50 ,  G06T7/73 ,  G06V10/774 ,  G06V10/82 ,  G06V20/46 ,  H04N19/136 ,  H04N19/147 ,  H04N19/184 ,  H04N19/436 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30032

摘要： A method of compressing and detecting target features of a medical video is presented herein. In some embodiments, the method may include receiving an uncompressed medical video comprising at least one target feature, compressing the uncompressed medical video to generate a compressed medical video based on a predicted location of the at least one target feature using a first pretrained machine learning model, and detecting the location of the at least one target feature of the compressed medical video using a second pretrained machine learning model. In some embodiments, the first pretrained machine learning model and the second pretrained machine learning model may be trained in tandem using domain-specific medical videos.

公开(公告)号：US11949893B2

公开(公告)日：2024-04-02

申请号：US17370879

申请日：2021-07-08

申请人： Huawei Technologies Co., Ltd.

发明人： Ye-Kui Wang ,  F N U Hendry

IPC分类号： H04N19/436 ,  H04N19/119 ,  H04N19/132 ,  H04N19/137 ,  H04N19/169 ,  H04N19/174 ,  H04N19/184 ,  H04N19/44 ,  H04N19/593 ,  H04N19/176 ,  H04N19/31 ,  H04N19/70

CPC分类号： H04N19/436 ,  H04N19/119 ,  H04N19/132 ,  H04N19/137 ,  H04N19/174 ,  H04N19/184 ,  H04N19/188 ,  H04N19/1883 ,  H04N19/44 ,  H04N19/593 ,  H04N19/176 ,  H04N19/31 ,  H04N19/70

摘要： A video coding mechanism is disclosed. The mechanism includes receiving a bitstream comprising one or more sub-pictures partitioned from a picture and a sub-picture level indicator indicating resource requirements for decoding a current sub-picture. The bitstream is parsed to obtain the sub-picture level indicator and the current sub-picture. Resources are allocated to decode the current sub-picture based on the sub-picture level indicator. The current sub-picture is decoded to create a video sequence by employing the allocated resources. The video sequence is forwarded for display.

公开(公告)号：US11943484B2

公开(公告)日：2024-03-26

申请号：US18116520

申请日：2023-03-02

申请人： Sun Patent Trust

发明人： Semih Esenlik ,  Matthias Narroschke ,  Thomas Wedi

IPC分类号： G06V10/00 ,  H04N19/174 ,  H04N19/30 ,  H04N19/423 ,  H04N19/436 ,  H04N19/46 ,  H04N19/52 ,  H04N19/597 ,  H04N19/70

CPC分类号： H04N19/70 ,  H04N19/174 ,  H04N19/30 ,  H04N19/423 ,  H04N19/436 ,  H04N19/46 ,  H04N19/52 ,  H04N19/597

摘要： A dependency indication is signaled within the beginning of a packet, that is, within the adjacent of a slice header to be parsed or a parameter set. This is achieved, for example, by including the dependency indication at the beginning of the slice header, preferably after a syntax element identifying the parameter set and before the slice address, by including the dependency indication before the slice address, by providing the dependency indication to a NALU header using a separate message, or by using a special NALU type for NALUs carrying dependent slices.