Tencent Technology (shenzhen) Company Limited

Zte Corporation

Yun Cao

Chengjie Wang

Jilin Li

Ying Tai

Hui Ni

Yanhao Ge

Yandan Zhao

Junwei Zhu

Weijian Cao

Xiaozhong Ji

Feida Zhu

Feiyue Huang

Rui Li

Yuan Huang

Shouhong Ding

Shaoxin Li

Keke He

Zhixiong Zhou

Xu Chen

Yichao Yan

Fengyan Dai

Junfeng Liao

Guoyan Mu

Pan Cheng

A facial image processing method includes: obtaining first optical flow information; obtaining, based on the first optical flow information, second optical flow information through an optical flow information prediction sub-model of an image processing model; generating, based on the first facial sample image and the second optical flow information, a predicted image of the first facial sample image through a generator of the image processing model; discriminating the predicted image and the second facial sample image through a discriminator of the image processing model to obtain a first discrimination result and a second discrimination result; and training the image processing model based on the first discrimination result, the second discrimination result, the predicted image, the second facial sample image, the first optical flow information, and the second optical flow information.

Facial image processing method and apparatus, device, and storage medium

An image processing method includes performing additional image feature extraction on a training source face image to obtain a source additional image feature, performing identity feature extraction on the training source face image to obtain a source identity feature, inputting a training template face image into an encoder in a to-be-trained face swapping model to obtain a face attribute feature, inputting the source additional image feature, the source identity feature, and the face attribute feature into a decoder in the face swapping model for decoding to obtain a decoded face image, obtaining a target model loss value based on an additional image difference between the decoded face image and a comparative face image, and adjusting the model parameters of the encoder and the decoder based on the target model loss value to obtain the trained face swapping model.

Image processing method and apparatus, computer device, storage medium, and computer program product

A method, an apparatus, and a device for image processing and a training method thereof are provided. The training method includes obtaining a sample image set, the sample image set comprising a first number of sample images; constructing an image feature set based on the sample image set, the image feature set comprising an image feature extracted from each of the sample images in the sample image set; obtaining a training image set, the training image set comprising a second number of training images; constructing multiple training image pairs based on the training image set and the image feature set; and training the image processing model based on the multiple training image pairs.

Training method of image processing model, image processing method, apparatus, and device

A face image processing method and apparatus, a face image display method and apparatus, and a device are provided, belonging to the technical field of image processing. The method includes: acquiring a first face image of a person; invoking an age change model to predict a texture difference map of the first face image at a specified age, the texture difference map being used for reflecting a texture difference between a face texture in the first face image and a face texture of a second face image of the person at the specified age; and performing image processing on the first face image based on the texture difference map to obtain the second face image.

Face image processing method and apparatus, face image display method and apparatus, and device

A target tracking method is provided for a computer device. The method includes determining a target candidate region of a current image frame; capturing a target candidate image matching the target candidate region from the current image frame; determining a target region of the current image frame according to an image feature of the target candidate image; determining motion prediction data of a next image frame relative to the current image frame by using a motion prediction model and according to the image feature of the target candidate image; and determining a target candidate region of the next image frame according to the target region and the motion prediction data.

Target tracking method, computer device, and storage medium

This application relates to an image processing method and apparatus, a facial recognition method and apparatus, a computer device, and a readable storage medium. The image processing method includes: obtaining a target image comprising an object wearing glasses; inputting the target image to a glasses-removing model comprising a plurality of sequentially connected convolution squeeze and excitation networks; obtaining feature maps of feature channels of the target image through convolution layers of the convolution squeeze and excitation networks; obtaining global information of the feature channels according to the feature maps through squeeze and excitation layers of the convolution squeeze and excitation networks, learning the global information, and generating weights of the feature channels; weighting the feature maps of the feature channels according to the weights through weighting layers of the convolution squeeze and excitation networks, respectively, and generating weighted feature maps; and generating a glasses-removed image corresponding to the target image according to the weighted feature maps through the glasses-removing model. The glasses in the image can be effectively removed using the method.

Image processing method and apparatus, facial recognition method and apparatus, and computer device

This application relates to feature point positioning technologies. The technologies involve positioning a target area in a current image; determining an image feature difference between a target area in a reference image and the target area in the current image, the reference image being a frame of image that is processed before the current image and that includes the target area; determining a target figure point location of the target area in the reference image; determining a target feature point location difference between the target area in the reference image and the target area in the current image according to a feature point location difference determining model and the image feature difference; and positioning a target feature point in the target area in the current image according to the target feature point location of the target area in the reference image and the target feature point location difference.

Feature point positioning method, storage medium, and computer device

The present invention discloses a method for terminal access, and this method includes: receiving an access request sent by a terminal; analyzing the access request to obtain a service type of the terminal; determining a number of residual equivalent users according to a difference between an access equivalent user number threshold corresponding to the service type of the terminal currently and a number of accessed terminals; and determining whether to respond to the access request according to the number of the residual equivalent users and a preset minimum residual equivalent user threshold. The present invention further discloses an apparatus for accessing the terminal. With the present invention, dynamic variation of the wireless environment can be adapted, QoS with higher quality can be provided for the users, and the experience and the feeling of the users are improved.

Method and apparatus for terminal access

A decompression method for communication network is provided, in which such fields as an SN are compressed by using an ROHC scheme. The ROHC uses a WLSB algorithm to compress some fields which change regularly, and decodes by using the decompressor's context through transmitting the low significant bits in these fields. In order to avoid using the inefficient ergodic method and the incorrect direct replacing method in low bits, based on the mathematical characteristics of the definition of interpretation intervals, decoding is performed such that the low bits is determined by the received k significant bits while the high bits is determined jointly by the local storage information and these k significant bits. Its decoding method can be used for decompression of an SN, a TS and an IP-ID in an ROHC compression.

Growing community of inventors

Shenzhen, China

Yun Cao