Huawei Technologies Co., Limited

Huawei Technologies Co., Ltd. and Huawei Technologies Co., Ltd.

Tizheng Wang

Jiali Fu

Xueyan Huang

Lina Tao

Duan Li

Hongkai Zhou

Huali Wang

Jian Ye Chen

Chen Yang

Shisheng Zheng

Feilong Ma

Xiujie Huang

Jingduo Tian

Xiaoe Wang

Yu Ngok Li

Yalin Liu

Yu Meng Li

Wei Song

Wei Wang

Haiting Li

Wei Wei

Qi Zhang

Rongdao Yu

Qi Yu

Simon Ekstrand

Maosheng Huang

Bin Xia

Jiang Li

Changcai Lai

Jun Cao

Min Ye

Fan Fan

Fredrik Andreasson

Wei Su

Qingping Wang

Lelin Wang

Yangpo Xu

Xingguang Song

An Li

Jingyu Zhang

Biao Liang

Jianbin Liu

Zhipeng Chen

Xionghui He

Ren Zhu

Zongwu Wu

Zhaolei Xiao

Yuanfeng Xiong

Na Qi

Yingqiang Zhang

Er Li

Chen Su

Xiangyu Zhao

Jinlei Zhang

Lifu Chen

Dehan Li

Yang Fu

Naoya Iwamoto

Caihua Lei

Shiqiang Peng

This application provides an image processing method, including: performing stabilization on two adjacent image frames of a video stream acquired by a camera to obtain cropped areas, and performing perspective distortion correction on the cropped areas obtained through stabilization. Because the cropped areas output after stabilization is performed on the two adjacent frames include same or basically same content, it can be ensured that a subsequently generated video is smooth and stable. In this application, position relationships, for perspective distortion correction, between the cropped areas obtained through stabilization are further mapped, so that degrees or effects of perspective distortion correction of the adjacent frames of the subsequently generated video are the same, in other words, degrees of transformation of a same object in the images are the same.

Image processing method and related device

Methods, devices, and systems for digital space management in virtual reality and augmented reality are described. A method can include a terminal that logs in to a preset application based on a first user identifier, presents a first interface, where the first interface includes a virtual space registration option. In response to an enabling operation of a user for the virtual space registration option, the terminal photographs a first scene to obtain a preview stream, obtains a target geometry, and sends the first user identifier, the preview stream, and the target geometry to a server. The preview stream and the target geometry are used to determine a target virtual space in which a user with the first user identifier has virtual content editing permission in a first virtual space. The first virtual space is a virtual space corresponding to a real world including the first scene. The target geometry is used to represent a form of the target virtual space.

Digital space management method, apparatus, and device

An image transformation method includes obtaining a first image for a target scenario by using a front-facing camera, where the target scenario includes a face of a target person; obtaining a target distance between the face of the target person and the front-facing camera; and when the target distance is less than a preset threshold, performing first processing on the first image to obtain a second image. The first processing includes performing distortion correction on the first image based on the target distance. The face of the target person in the second image is closer to a real appearance of the face of the target person than the face of the target person in the first image.

Image transformation method and apparatus

Embodiments of this application provide an audio data processing method and apparatus, and a sound box system, which are related to the field of audio technologies, and improve sound quality of an audio playing device. The sound box system includes a full-frequency sound box and a low-frequency sound box. The full-frequency sound box is physically connected to the low-frequency sound box by using a first fastening part of the full-frequency sound box and a second fastening part of the low-frequency sound box. Furthermore, the full-frequency sound box communicates with the low-frequency sound box by using a first communication part of the first fastening part and a second communication part of the second fastening part, where the first fastening part and the second fastening part are a group of paired connection parts, and the first communication part and the second communication part are a group of paired communication parts.

Audio data processing method and apparatus, and sound box system

The present disclosure discloses a preview-image display while a terminal device photographs a picture. The method comprises: obtaining, by a terminal device, a first preview image and a second preview image, wherein the first preview image is based on a current picture in a first mode and the second preview image is based on the current picture in a second mode; and displaying, by the terminal device, a first part of the first preview image and a second part of the second preview image in a preview area, wherein the first part of the first preview image and the second part of the second preview image constitute a third preview image based on the current picture.

Preview-image display method and terminal device

An image processing method, where a target area and a background area are determined in an image by performing mask segmentation on the image. Different color processing modes are applied to the target area and the background area, such that luminance of the target area is greater than luminance of the background area, or chrominance of the target area is greater than chrominance of the background area, and a main object corresponding to the target area is more prominently highlighted. This enables a terminal user to have a movie special effect during photographing or video photographing, and improves photographing experience of the user. In addition, the present disclosure further provides a flicker elimination method, such that a color change of video content is smoother and more natural.

Image processing method and apparatus, and device

An image processing method includes determining a target area and a background area in an image by performing mask segmentation on the image. Different color processing modes are applied to the target area and the background area, so that luminance of the target area is greater than luminance of the background area, or chrominance of the target area is greater than chrominance of the background area, and a main object corresponding to the target area is more prominently highlighted.

A content push method is provided. The method is applied to a terminal, which includes a first set of cameras. The method includes: when the terminal is in a screen-locked state and an off-screen is woken up, capturing a first set of face images of a user by using the first set of cameras; determining whether the first set of face images matches a registered user; if the first set of face images matches the registered user, performing, by the terminal, an unlocking operation, and determining a facial attribute of the user based on the first set of face images; determining a to-be-pushed media resource based on the facial attribute; and pushing the media resource in an interface displayed after the terminal is unlocked.

Content push method and apparatus, and device

The present disclosure discloses a preview-image display while a terminal device photographs a picture. The method comprises: obtaining a first preview image and a second preview image, wherein the first preview image is generated based on a first photographing mode and the second preview image is generated based on a second photographing mode; and displaying a first part of the first preview image and a second part of the second preview image at the same time.

The present invention discloses an object modeling and movement method. The method is applied to a mobile terminal, and the mobile terminal includes a color camera and a depth camera. The method includes: performing panoramic scanning on a target object by using the color camera and the depth camera, to obtain a 3D model of the target object; obtaining a target skeletal model; fusing the target skeletal model and the 3D model of the target object; obtaining a target movement manner; and controlling the target skeletal model in the target movement manner, to animate the 3D model of the target object in the target movement manner. This can implement integration from scanning, 3D reconstruction, skeletal rigging, to preset animation display for an object on one terminal, thereby implementing dynamization of a static object, and increasing interest in using the mobile terminal by a user.

Object modeling and movement method and apparatus, and device

A photographing method is provided. In the method, based on a video call between terminals at two places, each terminal previews, in a preset template, real-time preview video streams of the two parties. The two parties may separately adjust a picture of a local preview stream, and obtain a respective high-definition image through snapping when a preview group photo image is satisfying. Through file backhaul, one terminal can generate a high-resolution remote group photo based on snapped high-definition images of the terminals, a picture adjustment parameter during snapping, and the preset template.

Photographing method, apparatus, and device

Embodiments of the present invention provide a method for filtering an object. The method includes: displaying an object management interface; detecting a location that is on the object management interface and that is touched by a user; determining, according to the touched location and a pressure value applied to the touched location, when the pressure value is greater than a preset threshold, a first type required by the user; and obtaining, through filtering in the object management interface, and presenting all objects of the first type. By using this method, the user can effectively obtain, through filtering in the object management interface, the presented objects of the first type, purposely locate, among disorderly messages or files, a type in which the user is interested, and filter out information of other types.

Method and apparatus for filtering object by using pressure

An embodiment of the present invention discloses an image processing method, an apparatus, and a device. The method is applied to a terminal having two specially manufactured cameras. A first sub-image that is of a to-be-photographed object and that is photographed by a first camera is obtained, where a corresponding field-of-view range is [0, &#x3b8;]; a second sub-image that is of the to-be-photographed object and that is photographed by a second camera is obtained, where a corresponding field-of-view range is [&#x3b8;, &#x3b8;], and quality of the first sub-image and the second sub-image satisfies a definition requirement of an extra-large aperture; and the first sub-image and the second sub-image are spliced and fused to obtain a target image that has a larger field-of-view range and satisfies the extra-large aperture.

Image processing method, apparatus, and device

The present invention discloses a sound processing method and apparatus. The method is applied to a non-video-call scenario. The method includes: when it is detected that a camera of a terminal is in a shooting state, collecting a sound signal by using the two microphones at the top of the terminal; calculating an interaural level difference between the two microphones based on collected sound signals according to a preset first algorithm; determining whether the interaural level difference meets a sound source direction determining condition; if the determining condition is met, determining, based on the interaural level difference, whether the sound signal includes a rear sound signal, where the rear sound signal is a sound signal whose sound source is located behind the camera; and if it is determined that the sound signal includes a rear sound signal, filtering out the rear sound signal from the sound signal.

Sound processing method and apparatus

Growing community of inventors

Shenzhen, China

Tizheng Wang