Tencent Technology (shenzhen) Company Limited

Tencent Technology Company Limited

Pei Cheng

Bin Fu

Gang Yu

Mengren Qian

Yuxuan Yan

Yu Gao

Yang Ding

Youcheng Ben

Jingjin Zhou

Qiang Li

Chao Wang

Xiaolong Zhu

Rui Zhang

Xiao Li

Xiao Zhou

Keyi Shen

Xuan Qiu

Meng Ren Qian

Yirong Zeng

Xiaoqi Li

Yuan Hua

Ruixue Shen

Xiaohang Ren

Zhi Bin Wang

Disclosed is a method for training an expression transfer model performed by a computer device, the method including: obtaining a source domain facial image of a first object, a target domain facial image of a second object and a facial feature image associated with the target domain facial image; applying the facial feature image and the source domain facial image to an expression transfer model to obtain a synthesized facial image of the first object; applying the synthesized facial image and the target domain facial image to a discriminative network model obtain two discrimination results; applying the synthesized facial image and the target domain facial image to an image classification model to obtain a category feature vector for identifying a difference between the synthesized facial image and the target domain facial image; and updating the expression transfer model according to the category feature vector and the discrimination results.

Training method for expression transfer model, expression transfer method and apparatus

An embodiment of this application discloses an artificial intelligence-based image generation method performed by a computer device. The method includes: acquiring a source image including a target object whose pose is to be transformed, and a target image including a reference object presenting a target pose; determining a pose transition matrix according to a model pose corresponding to the pose of the target object and a model pose corresponding to the target pose of the reference object; extracting a basic appearance feature of the target object from the source image; processing the basic appearance feature based on the pose transition matrix, to obtain a target appearance feature of the target object in the target pose; and generating a target synthetic image of the target object in the target pose based on the target appearance feature.

Artificial intelligence-based image generation method, device and apparatus, and storage medium

An image processing method and apparatus, a device, and a storage medium. The image processing method includes: performing preliminary segmentation recognition on a raw image by using a first segmentation model to obtain a candidate foreground image region and a candidate background image region of the raw image; recombining the candidate foreground image region, the candidate background image region, and the raw image to obtain a recombined image, pixels in the recombined image being in a one-to-one correspondence with pixels in the raw image; and performing region segmentation recognition on the recombined image by using a second segmentation model to obtain a target foreground image region and a target background image region of the raw image.

Image processing method and apparatus, device and storage medium

A computing device obtains a to-be-optimized image. The device aligns the to-be-optimized image to obtain a to-be-optimized aligned image. The to-be-optimized aligned image includes a target region having points of objects that are distributed in a standard position. The computing device uses the to-be-optimized aligned image as an inputs to a generation network. The device performs feature extraction on the to-be-optimized aligned image using the generation network, to obtain an optimized image. The generation network is obtained by training a to-be-trained generative adversarial deep neural network model according to a low-quality image pair and a joint loss function. The low-quality image pair includes a target image and a low-quality image corresponding to the target image.

Image optimization method and apparatus, computer storage medium, and electronic device

Embodiments of this application disclose a video data processing method and apparatus, and a storage medium. After historical and current video frames are acquired from a video stream, two point position sets of a human body are obtained from the historical video frame and the current video frame, respectively. A jitter amplitude of a human body key point in the current video frame is analyzed according to the point position set of the human body in the current video frame and the point position set of the human body in the historical video frame; an adjustment reference position of the human body in the current video frame is determined according to the jitter amplitude; and subsequently a human body part below the adjustment reference position in the current video frame is adjusted and the adjusted current video frame is outputted for display as part of the video stream.

Video data processing method and apparatus, and storage medium

An image processing method includes: obtaining audio data corresponding to a reality scene image acquired in real time; dynamically determining attribute information of a virtual object according to the audio data, the attribute information indicating a visual state of the virtual object; identifying a target object from the reality scene image; determining, according to the target object, a fusion location of the virtual object determined according to the attribute information in the reality scene image according to the target object; fusing the virtual object determined according to the attribute information into the reality scene image according to the fusion location, the virtual object presenting different visual states that correspond to different attribute information dynamically determined according to the audio data.

Image processing method, storage medium, and computer device

The present disclosure provides an image processing method, including: recognizing a source object in a source image, and determining, according to feature points of the source object, an orientation and a size of the source object; adjusting, according to matching relationships between the orientation and the size of the source object and the orientation and the size of the target object, the orientation and the size of the source object; adjusting a shape of the source object and a shape of the target object according to an average shape of the source object and an average shape of the target object; and fusing, in real time, the source image and the target image in a manner of aligning the shape of the source object with the shape of the target object.

Image processing method, apparatus, terminal, and storage medium

The present disclosure discloses an image processing method, including: recognizing basic feature points of a source object in a source image and basic feature points of a base object in a base image; determining, according to distribution of the basic feature points in each of the images, auxiliary feature points that meet a filling condition according to the distribution in a corresponding image; determining feature points of a same type in the source object and the base object, the feature points of the same type including basic feature points of a same type and auxiliary feature points of a same type in the source object and the base object; determining average feature points according to positions of the feature points of the same type; deforming the source object and the base object according to the average feature points; and fusing the deformed source object with the deformed base object. The present disclosure further discloses an image processing apparatus, a terminal, and a storage medium.

Image processing method, apparatus, terminal, and storage medium for fusing images of two objects

Embodiments of this application disclose an image fusion method performed by a computing device. The method includes the following steps: obtaining source face image data of a current to-be-fused image and resource configuration information of a current to-be-fused resource, performing image recognition processing on the source face image data, to obtain source face feature points corresponding to the source face image data, and generating a source face three-dimensional grid of the source face image data according to the source face feature points, performing grid fusion by using a resource face three-dimensional grid and the source face three-dimensional grid to generate a target face three-dimensional grid, and performing face complexion fusion by using source complexion data of the source face image data and resource complexion data of resource face image data on the target face three-dimensional grid, to generate fused target face image data.

Image fusion method and device, storage medium and terminal

A method and system are provided. The method includes positioning facial feature base points in a face image in an obtained image. A deformation template is obtained, the deformation template carrying configuration reference points and configuration base points. In the facial feature base points, a current reference point is determined corresponding to the configuration reference point, and a to-be-matched base point is determined corresponding to the configuration base point. A target base point is determined that corresponds to the configuration base point and that is in a to-be-processed image. The target base point and the corresponding to-be-matched base point forming form a mapping point pair. A to-be-processed image point is mapped to a corresponding target location according to a location relationship between the target base point and the to-be-matched base point, and a location relationship between the mapping point pair and the to-be-processed image point.

Image deformation processing method and apparatus, and computer storage medium

A method for creating a collage among members of a chat group of a social networking application is performed at a terminal, comprising: generating a first collage using a user-selected collage template after receiving a user-selected picture for a predefined location in the user-selected collage template; generating a configuration file used for describing the first collage; and submitting the first collage and the configuration file to the social networking application, wherein the social networking application is configured to forward the first collage and the configuration file to another member of the chat group when there are one or more blank sections in the first collage and the other member of the chat group is configured to update the first collage by adding at least one picture to one of the one or more blank sections until there is no blank section in the first collage.

Growing community of inventors

Shenzhen, China

Pei Cheng