Tencent Technology (shenzhen) Company Limited

Sz Dji Technology Co., Ltd.

The Hong Kong University of Science and Technology

Tencent Technology Company Limited

Yonggen Ling

Yan Zhang

Linchao Bao

Xiangkai Lin

Wanchao Chi

Shenghao Zhang

Yu Zheng

Xinyang Jiang

Liang Qiao

Zhengyou Zhang

Fengming Zhu

Ang Liu

Weiyu Mo

Yu Zuo

Zeyu Yang

Li Qin Shen

Chong Wei Zhang

Haozhi Huang

Yibing Song

Dong Yu

Xiaolong Zhu

Yi Lin

Shaojie Shen

Yitong Wang

Zequn Jie

Yi Song

Jiawei Li

Kaiyong Zhao

Ang Li

Le Chen

Lin Chao Bao

Mu Hu

Zejian Yuan

Xue Fei Zhe

Sirui Gao

Ziyang Song

Ziyi Yin

Dongdong Bai

Zidong Cao

Tianbo Liu

Zhenfei Yang

Yajing Chen

Xuefei Zhe

A scene contour recognition method is provided. In the method, a plurality of scene images of an environment is obtained. Three-dimensional information of a target plane in the plurality of scene images is determined based on depth information for each of the plurality of scene images, The target plane corresponds to a target object in the plurality of scene images. A three-dimensional contour corresponding to the target object is generated by fusing the target plane in each of the plurality of scene images based on the three-dimensional information of the target plane in each of the plurality of scene images. A contour diagram of the target object is generated by projecting the three-dimensional contour onto a two-dimensional plane.

Scene contour recognition in video based on depth information

This application relates to a planar contour recognition method and apparatus, a computer device, and a storage medium. The method includes obtaining a target frame image collected from a target environment; fitting edge points of an object plane in the target frame image and edge points of a corresponding object plane in a previous frame image to obtain a fitting graph, the previous frame image being collected from the target environment before the target frame image; deleting edge points that do not appear on the object plane of the previous frame image, in the fitting graph; and recognizing a contour constructed by remaining edge points in the fitting graph as a planar contour.

Planar contour recognition method and apparatus, computer device, and storage medium

The present disclosure provides an image processing method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: obtaining a first three-dimensional image of a target object in a three-dimensional coordinate system; determining a target plane of the target object in the first three-dimensional image, the target plane comprising target three-dimensional points; projecting the target three-dimensional points to a two-dimensional coordinate system defined on the target plane, to obtain target two-dimensional points; determining a target polygon and a minimum circumscribed target graphic of the target polygon according to the target two-dimensional points; and recognizing the minimum circumscribed target graphic as a first target graphic of the target object in the first target three-dimensional image.

Image processing method and apparatus, electronic device, and computer-readable storage medium for identifying two-dimensional shapes using a depth image

A method for controlling motion of a legged robot includes: determining, according to state data of the legged robot at a start moment in a preset period, a candidate landing point of each foot in the preset period; determining, according to the state data at the start moment and the candidate landing point of each foot, a first correlation between a centroid position change parameter, a step duty ratio, a candidate landing point, and a foot contact force; determining, under a constraint of a constraint condition set, a target centroid position change parameter, a target step duty ratio, and a target landing point satisfying the first correlation; and controlling, according to the target centroid position change parameter, the target step duty ratio, and the target landing point, motion of the legged robot in the preset period.

Method and apparatus for controlling motion of legged robot, device, and medium

A method of depth map completion is described. A color map and a sparse depth map of a target scenario can be received. Resolutions of the color map and the sparse depth map are adjusted to generate n pairs of color maps and sparse depth maps of n different resolutions. The n pairs of color maps and the sparse depth maps can be processed to generate n prediction result maps using a cascade hourglass network including n levels of hourglass networks. Each of the n pair is input to a respective one of the n levels to generate the respective one of the n prediction result maps. The n prediction result maps each include a dense depth map of the same resolution as the corresponding pair. A final dense depth map of the target scenario can be generated according to the dense depth maps.

Image processing method, apparatus, and device, path planning method, apparatus, and device, and storage medium

A model training method includes obtaining an image sample set and brief-prompt information; generating a content mask set according to the image sample set and the brief-prompt information; generating a to-be-trained image set according to the content mask set; obtaining, based on the image sample set and the to-be-trained image set, a predicted image set through a to-be-trained information synthesis model, the predicted image set comprising at least one predicted image, the predicted image being in correspondence to the image sample; and training, based on the predicted image set and the image sample set, the to-be-trained information synthesis model by using a target loss function, to obtain an information synthesis model.

Model training method, media information synthesis method, and related apparatuses

This disclosure relates to a spatial calibration method and apparatus of a robot ontology coordinate system based on a visual perception device and a storage medium. The method includes: obtaining first transformation relationships; obtaining second transformation relationships; using a transformation relationship between a visual perception coordinate system and an ontology coordinate system as an unknown variable; and resolving the unknown variable based on an equivalence relationship between a transformation relationship obtained according to the first transformation relationships and the unknown variable and a transformation relationship obtained according to the second transformation relationships and the unknown variable, to obtain the transformation relationship between the visual perception coordinate system and the ontology coordinate system.

Visual perception device based spatial calibration method and apparatus for robot body coordinate system, and storage medium

A computer device extracts local features of sample images based on a first part of a convolutional neural network (CNN) model. The sample images comprise a plurality of images taken at the same place. The device; aggregates the local features into feature vectors having a first dimensionality based on a second part of the CNN model. The device obtains compressed representation vectors of the feature vectors based on a third part of the CNN model. The compressed representation vectors have a second dimensionality less than the first dimensionality. The device trains the CNN model, and obtains a trained CNN mode satisfying a preset condition in accordance with the training.

Method, apparatus, and electronic device for training place recognition model

An artificial intelligence-based action recognition method includes: determining, according to video data comprising an interactive object, node sequence information corresponding to video frames in the video data, the node sequence information of each video frame including position information of nodes in a node sequence, the nodes in the node sequence being nodes of the interactive object that are moved to implement a corresponding interactive action; determining action categories corresponding to the video frames in the video data, including: determining, according to the node sequence information corresponding to N consecutive video frames in the video data, action categories respectively corresponding to the N consecutive video frames; and determining, according to the action categories corresponding to the video frames in the video data, a target interactive action made by the interactive object in the video data.

Artificial intelligence-based action recognition method and related apparatus

A method for determining motion information is provided to be executed by a computing device. The method includes: determining a first image and a second image, the first image and the second image each including an object; determining a first pixel region based on a target feature point on the object in the first image; determining a second pixel region according to a pixel difference among a plurality of first pixel points in the first pixel region and further according to the target feature point; and obtaining motion information of the target feature point according to the plurality of second pixel points and the second image, the motion information being used for indicating changes in locations of the target feature point in the first image and the second image.

Method and device for determining motion information of image feature point, and task performing method and device

A video sound-picture matching includes: acquiring a voice sequence; acquiring a voice segment from the voice sequence; acquiring an initial position of a start-stop mark and a moving direction of the start-stop mark from an image sequence; determining an active segment according to the initial position of the start-stop mark, the moving direction of the start-stop mark, and the voice segment; and synthesizing the voice segment and the active segment to obtain a video segment. In a video synthesizing process, the present disclosure uses start-stop marks to locate positions of active segments in an image sequence, so as to match the active segments having actions with voice segments, so that the synthesized video segments are more in line with natural laws of a character during speaking, and have better authenticity.

Sound-picture matching method of video, related apparatus, and storage medium

An image processing method and apparatus, a computer-readable medium, and an electronic device are provided. The image processing method includes: respectively projecting, according to a plurality of view angle parameters corresponding to a plurality of view angles, a face model of a target object onto a plurality of face images of the target object acquired from the plurality of view angles, to determine correspondences between regions on the face model and regions on the face image; respectively extracting, based on the correspondences and a target region in the face model that need to generate a texture image, images corresponding to the target region from the plurality of face images; and fusing the images that correspond to the target region and that are respectively extracted from the plurality of face images, to generate the texture image.

Image processing method and apparatus, computer-readable medium, and electronic device

A method for controlling a UAV in an environment includes receiving first and second sensing signals from a vision sensor and a proximity sensor, respectively, coupled to the UAV. The first and second sensing signals include first and second depth information of the environment, respectively. The method further includes selecting the first and second sensing signals for generating first and second portions of an environmental map, respectively, based on a suitable criterion associated with distinct characteristics of various portions of the environment or distinct capabilities of the vision sensor and the proximity sensor, generating first and second sets of depth images for the first and second portions of the environmental map, respectively, based on the first and second sensing signals, respectively, combining the first and second sets of depth images to generate the environmental map; and effecting the UAV to navigate in the environment using the environmental map.

Multi-sensor environmental mapping

Embodiments of this application disclose a method for displaying a virtual character in a plurality of real-world images captured by a camera is performed at an electronic device. The method includes: capturing an initial real-world image using the camera; simulating a display of the virtual character in the initial real-world image; capturing a subsequent real-world image using the camera after a movement of the camera; determining position and pose updates of the camera associated with the movement of the camera from tracking one or more feature points in the initial real-world image and the subsequent real-world image; and adjusting the display of the virtual character in the subsequent real-world image in accordance with the position and pose updates of the camera associated with the movement of the camera.

Position and pose determining method, apparatus, smart device, and storage medium

A computer application method for generating a three-dimensional (3D) face model is provided, performed by a face model generation model running on a computer device, the method including: obtaining a two-dimensional (2D) face image as input to the face model generation model; extracting global features and local features of the 2D face image; obtaining a 3D face model parameter based on the global features and the local features; and outputting a 3D face model corresponding to the 2D face image based on the 3D face model parameter.

Computer application method and apparatus for generating three-dimensional face model, computer device, and storage medium

Growing community of inventors

Shenzhen, China

Yonggen Ling