Huawei Technologies Co., Limited

Future Wei Technologies, Inc.

Jiantong Zhou

Shan Liu

Bin Li

Haitao Yang

Bin Wang

Oscar Au

Sixin Lin

Xingyu Zhang

Haoping Yu

Shan Gao

Houqiang Li

Mingyuan Yang

Huanbang Chen

Jiali Fu

Cunbin Pan

Yuntan Fang

Jun Zha

Yin Zhao

Xiaozhen Zheng

Zhijie Zhao

Jing Jing Xiao

Hu Chen

Roman Igorevich Chernyak

Sriram Sethuraman

Peiyun Di

Qingpeng Xie

Zhe Wang

Jeeva Raj A

Victor Alexeevich Stepin

Sagar Kotecha

Quanhe Yu

Ruihua Li

Jin Song

Zhuoyi Lv

Yi Song

Lianhuan Xiong

Changqi Hu

Bingyin Xia

Weiwei Xu

Jay Nitin Shingala

Zhaolei Xiao

Maozheng Liu

Xing Wen

Jose Alvarez

Zhenhua Wu

Yifan Fu

Xuhong Zeng

Pengxin Zeng

An intra-frame decoding method includes obtaining, from a video code stream, prediction mode information of a first signal component of a current block; determining a prediction mode of the first signal component of the current block from a prediction mode set of the first signal component of the current block according to the prediction mode information of the first signal component of the current block, where the prediction mode set of the first signal component of the current block includes at least one of a linear model above (LMA) mode and a linear model left (LML) mode; obtaining a predicted value of a first signal component sampling point of the current block; and obtaining a reconstructed value of the first signal component sampling point of the current block according to the predicted value of the first signal component sampling point of the current block.

Intra-frame prediction and decoding methods and apparatuses for image signal

Embodiments of this application disclose example apparatuses, methods, and computer program products for extracting a feature from an image of a scene. One example apparatus comprises at least one processor and one or more memories coupled to the at least one processor and storing programming instructions for execution by the at least one processor to, in response to a feature extraction event, extract a feature from first image data representing a first image of a scene, wherein the feature extraction event is based on second image data representing a second image of the scene.

Image processing apparatus and method for feature extraction

This application provides a video processing method and apparatus. The method includes: adding, by a server, perception attribute information of an object and spatial location information of the object to a video bitstream or a video file, and encapsulating the video bitstream or the video file, where the perception attribute information is used to indicate a property presented when the object is perceived by a user; and obtaining, by a terminal device, the video bitstream or the video file that carries the perception attribute information of the object and the spatial location information of the object, and performing perception rendering on a perception attribute of the object based on behavior of the user, the perception attribute information of the object and the spatial location information of the object.

Video processing method and apparatus

A high dynamic range image processing method and apparatus, to improve a display effect of a high dynamic range image. The method includes: obtaining image information of a to-be-processed high dynamic range (HDR) image, the image information includes a maximum RGB component value of a first pixel corresponding to a first percentage and a maximum RGB component value of a second pixel corresponding to a second percentage; determining a maximum reference value of the HDR image; determining a maximum luminance modification value of the HDR image based on the maximum reference value and a plurality of preset hierarchy intervals, where the maximum luminance modification value is used to modify a largest value in maximum RGB component values of the plurality of pixels included in the HDR image; and adjusting a dynamic range of the HDR image based on the maximum luminance modification value.

High dynamic range image processing method and apparatus

An intra-frame decoding method includes obtaining, from a video code stream, prediction mode information of a first signal component of a current block, determining a prediction mode of the first signal component of the current block from a prediction mode set of the first signal component of the current block according to the prediction mode information of the first signal component of the current block, where the prediction mode set of the first signal component of the current block includes at least one of a linear model above (LMA) mode and a linear model left (LML) mode; obtaining a predicted value of a first signal component sampling point of the current block; and obtaining a reconstructed value of the first signal component sampling point of the current block according to the predicted value of the first signal component sampling point of the current block.

This application provides a pixel collection circuit comprising an optical-to-electrical converter circuit configured to convert a collected optical signal into an analog signal; an analog-to-digital converter circuit configured to: receive the analog signal from the optical-to-electrical converter circuit; and perform analog-to-digital conversion on the analog signal to obtain a digital signal; a differential circuit configured to: receive the digital signal from the analog-to-digital converter circuit; and obtain a difference signal between a digital signal of a previous triggering moment and the digital signal of a current triggering moment; the previous triggering moment and the current triggering moment are determined by at least a digital clock signal; a comparison circuit configured to receive the difference signal from the differential circuit, and output a pulse signal. A digital component is used to implement the pixel collection circuit in the dynamic vision sensor, so as to reduce noise, reduce interference, and facilitate debugging.

Pixel collection circuit, dynamic vision sensor, and image capture device

The present disclosure relates to encoding of video image using coding parameters, which are adapted based on events related to motion within the video image. Image content is captured by a standard image sensor and an event-triggered sensor, providing an event-signal indicating changes (e.g. amount and time-spatial location) of image intensity. Objects are detected within the video image, based on the event signal assessing motion of the object, and their textures extracted. The spatial-time coding parameters of the video image are determined based on the location and strength of the event signal, and the extent to which the detected objects moves.

Event-based adaptation of coding parameters for video image encoding

An intra-frame decoding method includes obtaining, from a video code stream, prediction mode information of a first signal component of a current block, determining a prediction mode of the first signal component of the current block from a prediction mode set of the first signal component of the current block according to the prediction mode information of the first signal component of the current block, where the prediction mode set of the first signal component of the current block includes at least one of a linear model above (LMA) mode and a linear model left (LML) mode, obtaining a predicted value of a first signal component sampling point of the current block, and obtaining a reconstructed value of the first signal component sampling point of the current block according to the predicted value of the first signal component sampling point of the current block.

This application provides a dynamic vision sensor. The sensor converts an optical signal into an electrical signal by using a photoelectric conversion unit, to generate a photovoltage; performs second-order difference on the photovoltage by using a second-order differential circuit; and generates a second-order event signal based on a result of second-order difference. A camera including the sensor can generate an image based on the second-order event signal, where the image represents a change of a light change speed.

Dynamic vision sensor

A method includes obtaining a first motion vector of a motion compensation unit included in an affine code block. The method also includes determining a second motion vector based on the first motion vector, where a precision of the second motion vector matches a motion vector precision of a storage unit corresponding to the motion compensation unit. The method further includes determining a third motion vector based on the second motion vector, where there is a preset correspondence between the third motion vector and the second motion vector, and the third motion vector is used for subsequent encoding/decoding processing.

Method and apparatus for determining motion vector of affine code block

An image prediction method and apparatus includes obtaining predicted motion information of an image block; determining an initial predicted block of the image block according to the predicted motion information and a reference image of the image block; performing, according to the predicted motion information, L iterative searches in the reference image using an integer pixel step size to obtain an intermediate predicted block of the image block; performing a single search in the reference image using a fractional pixel step size to obtain M predicted blocks of the image block; determining a target predicted block of the image block according to the M predicted blocks and the intermediate predicted block; and obtaining a predicted value of a pixel value of the image block according to a pixel value of the target predicted block.

Image prediction method and apparatus

A chroma component prediction method, comprising obtaining reference samples of a current block, wherein the reference samples comprise a luma reference sample array and a chroma reference sample array, obtaining a correlation parameter based on the luma reference sample array and the chroma reference sample array, and calculating a prediction value of a chroma component of the current block based on a luma component of the current block and the correlation parameter, wherein the reference samples comprise samples on top of the current block and on a top right of the current block, or the reference samples comprise samples on a left of the current block and on a bottom left of the current block.

A video coding device selects a current block for sub-block based affine inter-prediction, and derives a sub-block size for a sub-block of the current block. The sub-block size includes a sub-block width and a sub-block height. The device determines a unidirectional width threshold (TwU), a bidirectional width threshold (TwB), a unidirectional height threshold (ThU), and a bidirectional height threshold (ThB), where a total value of TwB and ThB exceeds a total value of TwU and ThU. The device determines that the affine inter-prediction is unidirectional inter-prediction or bidirectional inter-prediction. Based on the determination, the device applies the TwU or the TwB to the sub-block width, and applies the ThU or the ThB to the sub-block height. The device then derives a motion vector for the sub-block based on motion vectors for the current block, the sub-block width, and the sub-block height.

Restriction on sub-block size derivation for affine inter prediction

A mechanism of video coding is provided. The mechanism includes generating a reconstructed video frame. Noise suppression filter parameters are determined by partitioning the reconstructed video frame into blocks and matching the blocks to create patches. The noise suppression filter parameters are then determined based on the patches by creating a transformed matrix of patch frequencies. The noise suppression filter parameters include a noise estimation parameter that is a function of patch frequency. The noise suppression filter parameters are then employed to apply a noise suppression filter to the reconstructed video frame.

Noise suppression filter parameter estimation for video coding

An intra-frame decoding method is provided. The method includes: obtaining, from a video code stream, prediction mode information of a first signal component of a current block, determining a prediction mode of the first signal component of the current block from a prediction mode set of the first signal component of the current block according to the prediction mode information of the first signal component of the current block, where the prediction mode set of the first signal component of the current block includes at least one of a linear model above (LMA) mode and a linear model left (LML) mode, obtaining a predicted value of a first signal component sampling point of the current block, and obtaining a reconstructed value of the first signal component sampling point of the current block according to the predicted value of the first signal component sampling point of the current block.

Growing community of inventors

Shenzhen, China

Jiantong Zhou