Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Shu Liu

Jiaya Jia

Xiaoyong Shen

Yuwing Tai

Hua Li

Li Jiang

Yi Chen

Jia Ya Jia

Qi Liu

Yu Wing Tai

Xiao Yong Shen

Yilun Chen

Lu Qi

Xinlong Wang

Ruo Bing Xie

Le Yu Lin

Liying Lu

An image processing method includes: obtaining an image, and performing feature extraction on the image; generating at least one candidate region of the image, and mapping the at least one candidate region into a feature map of the image, one candidate region including one instance; processing the mapped feature map based on a target network for instance segmentation; and indicating an overall structure of an occluded instance in the image by using a perspective mask, and indicating an invisible part of the occluded instance by using a non-perspective mask, the perspective mask and the non-perspective mask representing a relative occlusion relationship of the occluded instance.

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

The present disclosure provides a target image generation method. The method includes obtaining a first parsed image and a first pose image based on an original image, the first parsed image being an image labeled with parts of an object in the original image, the first pose image representing a pose of the object in the original image; inputting the first parsed image, the first pose image, and a second pose image representing a target pose into a first image generation model, and determining, a first transformation parameter and adjusting the first parsed image based on the first transformation parameter to obtain a target parsed image, a pose of the object in the target parsed image being the target pose; and inputting a first combined image and a second combined image into a second image generation model, and adjusting the first combined image to obtain a target image.

Target image generation method and apparatus, server, and storage medium

A media information recommendation is provided by obtaining at least two types of media attribute information in which a target user is interested. The determination is based on target nodes corresponding to pieces of media attribute information in a heterogeneous preference network. Heterogeneous feature vectors of the target nodes and heterogeneous feature vectors of neighbor nodes of the target nodes are aggregated. Pieces of media information corresponding to aggregate feature vectors of which similarities satisfy a similarity condition to determine the media information recommendation for the target user.

Media information recommendation method and apparatus, electronic device, and storage medium

An object detection method and apparatus include obtaining a point cloud of a scene that includes location information of points. The point cloud is mapped to a 3D voxel representation. A convolution operation is performed on the feature information of the 3D voxel to obtain a convolution feature set and initial positioning information of a candidate object region is determined based on the convolution feature set. A target point is located in the candidate object region in the point cloud is determined and the initial positioning information of the candidate object region is adjusted based on the location information and target convolution feature information of the target point. Positioning information of a target object region is obtained to improve object detection accuracy.

Object detection method and apparatus, electronic device, and storage medium

This application relates to a point cloud segmentation method, a computer-readable storage medium, and a computer device. The method includes encoding a to-be-processed point cloud to obtain a shared feature, the shared feature referring to a feature shared at a semantic level and at an instance level; decoding the shared feature to obtain a semantic feature and an instance feature respectively; adapting the semantic feature to an instance feature space and fusing the semantic feature with the instance feature, to obtain a semantic-fused instance feature of the point cloud, the semantic-fused instance feature representing an instance feature fused with the semantic feature; dividing the semantic-fused instance feature of the point cloud, to obtain a semantic-fused instance feature of each point in the point cloud; and determining an instance category to which each point belongs according to the semantic-fused instance feature of each point.

Point cloud segmentation method, computer-readable storage medium, and computer device

Growing community of inventors

Shenzhen, China

Shu Liu