Baidu Online Network Technology (beijing) Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Baidu Online Network Technology Co., Ltd.

Zhibin Hong

Tianshu Hu

Kun Yao

Mingming Ma

Hanqi Guo

Tonghui Li

Ruigang Yang

Junyu Han

Jingtuo Liu

Jiaming Liu

Yanfu Zhang

Yuanzhang Chang

Dingfu Zhou

Shengyi He

Zhizhi Guo

Shengxian Zhu

Jieting Xue

Shihu Li

Borong Liang

Xusheng Zeng

Xiangda Yan

Provided are a video generation method and apparatus, a device and a storage medium, relating to the field of artificial intelligence and, in particular, to the fields of computer vision and deep learning. The method includes changing a character emotion of an original character image according to a character emotion feature of a to-be-generated video to obtain a target character image; and driving the target character image by use of a character driving network and based on a speech segment to obtain the to-be-generated video.

Video generation method, device and storage medium

Embodiments of the present disclosure provide a method for training a face fusion model and an electronic device. The method includes: performing a first face changing process on a user image and a template image to generate a reference template image; adjusting poses of facial features of the template image based on the reference template image to generate a first input image; performing a second face changing process on the template image to generate a second input image; inputting the first input image and the second input image into a generator of an initial face fusion model to generate a fused face area image; and inputting the fused image and the template image into a discriminator of the initial face fusion model to obtain a result, and performing backpropagation correction on the initial face fusion model based on the result to generate a face fusion model.

Method and apparatus for training face fusion model and electronic device

The present application discloses a face super-resolution realization method and apparatus, an electronic device and a storage medium, and relate to fields of face image processing and deep learning. The specific implementation solution is as follows: a face part in a first image is extracted; the face part is input into a pre-trained face super-resolution model to obtain a super-sharp face image; a semantic segmentation image corresponding to the super-sharp face image is acquired; and the face part in the first image is replaced with the super-sharp face image, by utilizing the semantic segmentation image, to obtain a face super-resolution image.

Face super-resolution realization method and apparatus, electronic device and storage medium

A method and apparatus for processing character image data are provided. A specific embodiment of the method can include: acquiring a video including character images of a first character as first data, and acquiring a video including character images of a second character as second data, the video including character images of the first character including a plurality of types of movement-state images; replacing a head image extracted from the first data with a head image extracted from the second data; replacing a face extracted from the first data with a face extracted from the second data; and replacing the face in the replaced head image with the replaced face to obtain a target head image.

Method and apparatus for processing character image data

A method for synthesizing a figure of a virtual object includes: obtaining a figure image of the virtual object, and original face images corresponding to a speech segment; extracting a first face key point of the face of the virtual object, and a second face key point of each of the original face images; processing the first face key point to generate a position and posture information of a first three-dimensional 3D face; processing each second face key point to generate vertex information of a second 3D face; generating a target face image corresponding to each original face image based on the position and the posture information of the first 3D face and the vertex information of each second 3D face; and synthesizing a speaking figure segment of the virtual object, corresponding to the speech segment, based on the figure image of the virtual object and each target face image.

Method for synthesizing figure of virtual object, electronic device, and storage medium

The present disclosure provides a neural network model training method and apparatus, a living body detecting method and apparatus, a device and a storage medium. It is feasible to, with respect to different scenarios, respectively obtain picture samples under the scenarios, each picture sample having a tag, the tag including a living body or a non-living body and a corresponding scenario; and according to obtained picture samples, train to obtain a neural network model whose output is a feature vector which is discriminative for different scenarios. As such, when the living body detection is performed, it is possible to determine the feature vector of the to-be-detected picture according to the neural network model, then determine a picture sample matched with the to-be-detected picture, and regard the tag of the matched picture sample as the tag of the to-be-detected picture, thereby obtaining the detection result of the to-be-detected picture.

Neural network model training method and apparatus, living body detecting method and apparatus, device and storage medium

The application provides a virtual object image display method and apparatus, an electronic device and a storage medium, relates to the field of artificial intelligence, in particular to the field of computer vision and deep learning, and may be applied to virtual object dialogue scenarios. The specific implementation scheme includes: segmenting acquired voice to obtain voice segments; predicting lip shape sequence information for the voice segments; searching for a corresponding lip shape image sequence based on the lip shape sequence information; performing lip fusion between the lip shape image sequence and a virtual object baseplate to obtain a virtual object image; displaying the virtual object image. The application improves ability to obtain virtual object image.

Virtual object image display method and apparatus, electronic device and storage medium

A method, an apparatus, a device and a storage medium for three-dimensional reconstruction are provided. The method may include: acquiring a sequence of RGBD images of a target; determining a set of first three-dimensional key points of the target on each RGBD image for the each RGBD image in the sequence of the RGBD images; transferring the set of the first three-dimensional key points to a camera coordinate system to obtain a set of second three-dimensional key points of the target in the camera coordinate system; calculating an Euler angle of the each RGBD image based on the set of the second three-dimensional key points; selecting an RGBD image based on the Euler angle; and performing three-dimensional reconstruction of the target based on the selected RGBD image to obtain a three-dimensional model of the target.

Method, apparatus, device and storage medium for three-dimensional reconstruction

The present disclosure provides a video blending method, apparatus, electronic device and readable storage medium, and relates to computer vision technologies. A specific implementation solution is as follows: obtaining a predicted 3D face mesh of a facial image in each video frame images of the user video according to each video frame image of a user video and each video frame image of a template video; obtaining a predicted texture of the predicted 3D face mesh according to a user texture of a user 3D face mesh of the facial image in each video frame image of the user video and a template texture of a template 3D face mesh of the facial image in each video frame image of the template video; obtaining a rendered facial image of the predicted 3D face mesh according to the predicted 3D face mesh, the predicted texture and user face posture, and template face posture; performing blending processing for the rendered facial image and each video frame image of the template video to obtain a blended video frame image after the blending; performing synthesis processing for the blended video frame image to obtain a blended video.

Video blending method, apparatus, electronic device and readable storage medium

Embodiments of the present disclosure provide an expression recognition method, apparatus, electronic device and storage medium. An expression recognition model includes a convolutional neural network model, a fully connected network model and a bilinear network model. During an expression recognition process, after an image to be recognized is pre-processed to obtain a facial image and a key point coordinate vector, the facial image is computed by the convolutional neural network model to output a first feature vector, the key point coordinate vector is computed by the fully connected network model to output a second feature vector, the first feature vector and the second feature vector are computed by the bilinear network model to obtain second-order information, and an expression recognition result in turn is obtained according to the second-order information. During this process, robustness of gestures and illuminations is better, and accuracy of expression recognition is improved.

Expression recognition method, apparatus, electronic device, and storage medium

A method, an electronic device and a storage medium for expression driving are disclosed. The method may include: performing facial key point detection on a driven character in a first image to obtain a first facial key point sequence; performing the following processing for each second image of a plurality of second images obtained successively: performing facial key point detection on a driving character in the second image to obtain a second facial key point sequence; obtaining a difference between the second facial key point sequence and an expressionless key point sequence which has been determined previously according to an analysis on the second facial key point sequence for a previous second image, and performing expression drive rendering on the driven character based on the difference and the first facial key point sequence. The technical solution may enhance flexibility, interactivity, accuracy etc.

Method, apparatus, electronic device and storage medium for expression driving

Methods and apparatus for detecting an image type. A specific embodiment of the method includes: acquiring a first to-be-processed image and a second to-be-processed image; determining at least one first object image and at least one second object image in the first to-be-processed image and the second to-be-processed image respectively; and importing the first object image and the second object image corresponding to the first object image into an image type detection model to obtain image type information corresponding to the first object image and the second object image, for each of the at least one first object image, the image type detection model being used to determine an image type by depth of field information, and the image type information including a plane image and a stereo image. This embodiment enables accurate recognition of the image types of the to-be-processed images.

Method and apparatus for detecting image type

The present disclosure provides a living body detecting method and apparatus, a device and a storage medium. The method comprises: obtaining user pictures collected by a fixed-focal-length camera at a fixed position, the user pictures being full-length or half-length pictures; determining whether the user is a living body according to a clarity degree of collected user pictures and whether there is a rim. The solution of the present disclosure can be applied to simplify user's operations and improve accuracy of detection results.

Living body detecting method and apparatus, device and storage medium

The present disclosure provides an attack sample generating method and apparatus, a device and a storage medium, wherein the method comprises: training a generative network which is used to generate an attack picture with a real person's picture; upon completion of training, using the generative network to generate an attack picture, and regarding the generated attack picture as the attack sample. The solution of the present disclosure can be applied to overcome the problem of insufficiency of the attack samples.

Attack sample generating method and apparatus, device and storage medium

A method and apparatus for acquiring information. A specific embodiment of the method includes: acquiring a to-be-processed near-infrared image and scenario information corresponding to the to-be-processed near-infrared image, the scenario information being used to represent a scenario of acquiring the to-be-processed near-infrared image; searching for a pre-trained near-infrared image recognition model corresponding to the scenario information, the near-infrared image recognition model being used to identify near-infrared feature information from the to-be-processed near-infrared image; and importing the to-be-processed near-infrared image into the near-infrared image recognition model to obtain the near-infrared feature information of the to-be-processed near-infrared image. This embodiment speeds up the acquisition of the near-infrared feature information and improves the accuracy and efficiency of acquiring the near-infrared feature information.

Growing community of inventors

Beijing, China

Zhibin Hong