Unlock instant, AI-driven research and patent intelligence for your innovation.
Driving method for 2D virtual model, and equipment thereof
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of virtual model and driving method, applied in the field of image processing, can solve the problems of poor user experience, video freeze, poor user experience, etc.
Inactive Publication Date: 2017-08-08
PALMWIN INFORMATION TECH SHANGHAI
View PDF5 Cites 3 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0004] There is an existing expression driving method based on a single model, which establishes the motion correspondence between the source and the target by applying RBF to train the skeleton structure, and then performs real-time driving through the weights obtained through training. Changes can easily distort the model
[0005] To sum up, the driving method using virtual models in the existing technology has disadvantages such as poor user experience and easy distortion of the model, which cannot meet the requirements of using virtual models to replace users to express emotions during video calls. At the same time, because video calls transmit The whole video takes up a lot of network resources, and it is prone to video freezing, blurring or disconnection, and the user experience is not good.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0108] The embodiment of the present invention provides a driving method of a 2D virtual model, referring to figure 1 As shown, the method flow includes:
[0109] 101. Perform feature point positioning on the current face image, and obtain 2D coordinates of the feature points.
[0110] Specifically, the process includes:
[0111] extracting feature vectors for eye part feature points in the feature points, and performing feature dimensionality reduction on the feature vectors;
[0113] When the eyes are closed, the feature point coordinates of the upper eyelid of the eye part are moved to the feature point position of the lower eyelid.
[0114] 102. Obtain frontalized 3D coordinates of the feature points according to the 2D coordinates of the feature points.
[0115] Specifically, the process includes:
[0116] Obtaining the 3D ...
Embodiment 2
[0138] The embodiment of the present invention provides a driving method of a 2D virtual model, referring to figure 2 As shown, the method flow includes:
[0139] 201. Perform feature point positioning on the current face image, and obtain 2D coordinates of the feature points.
[0140] Specifically, a method based on shape regression can be used to locate the face feature points in the face image. Face feature point location is based on face detection, and further locates the eyes, eyebrows, nose and mouth contours of the face. The information near the feature points and the relationship between each feature point can be used to locate the feature points. For example, the algorithm in the paper "Facial animationretargeting framework using radial basis functions" is used to collect the 2D coordinates of 66 feature points of the face. Among them, Exemplarily, the feature point location of the face image can refer to image 3 Shown in a.
[0141] For feature point positioni...
Embodiment 3
[0218] The embodiment of the present invention provides an electronic device 5, referring to Figure 5 As shown, the electronic equipment includes:
[0219] The feature point positioning module 51 is used to perform feature point positioning on the current face image, and obtain the 2D coordinates of the feature points;
[0220] A frontalization module 52, configured to obtain the frontalized 3D coordinates of the feature points according to the 2D coordinates of the feature points;
[0221] The 3D coordinate acquisition module 53 of the 2D virtual model is used to acquire the 3D coordinates of the 2D virtual model;
[0222]Establish an expression base module 54, for establishing the 3D expression base of the 2D virtual model according to the regression relationship between the 3D coordinates of the 2D virtual model and the expression base data of the pre-established face modeldatabase;
[0223] A fitting coefficient acquisition module 55, configured to obtain a fitting coe...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention discloses a driving method for a 2D virtual model, and equipment thereof, wherein the driving method and the equipment belong to the field of image processing. The driving method comprises the steps of performing characteristic point positioning on a current face image, and acquiring a 2D coordinate of a characteristic point; acquiring a positive 3D coordinate of the characteristic point according to the 2D coordinate of the characteristic point; acquiring a 3D coordinate of the 2D virtual model, and establishing a 3D expression group of the 2D virtual model according to a regression relation between the 3D coordinate of the 2D virtual model and expression group data of a pre-established face modeldatabase; according to the positive 3D coordinate and the 3D expression group of the 2D virtual model, acquiring a fitting coefficient between the current face and the 3D expression group of the 2D virtual model; and driving the 2D virtual model according to the fitting coefficient. Through driving the 2D virtual model according to the fitting coefficient, a requirement of a user for replacing himself in video through the 2D virtual model is satisfied, and furthermore bandwidth in video calling is effectively reduced. Furthermore an embarrassment that a user does not want to expose face in an interaction process with a stranger is prevented, and user experience is improved.
Description
technical field [0001] The invention relates to the field of image processing, in particular to a driving method and device for a 2D virtual model. Background technique [0002] Virtual modelfacial expressionanimation is a hotspot in current research, and it has a very wide range of applications in fields such as virtual reality, digital entertainment, communication and video conferencing, and human interaction. [0003] With the popularization of mobile terminals and the decline of network bandwidth charges, video calls will become the first choice in the social field. Since strangers are reluctant to show their faces at the beginning of communication, a communication tool is urgently needed to replace the video images of both parties. Virtual expression mapping will be a better choice. It can not only use virtual characters to replace users to express emotions, but also save a lot of bandwidth, and it can be completed only by sending corresponding parameters. [0004] ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More