Method and system for driving three-dimensional human face cartoon based on video

Abstract

The invention discloses a method and a system for driving three-dimensional facial animation, which is based on video. The method can comprise the following steps that: a facial expression in a video image is identified; and an organ needing deformation is deformed according to expression identification results and a preset driving rule corresponding to the expression, so as to obtain three-dimensional facial animation. Compared with the prior art, the invention has the advantages that the method first identifies the expression of a facial image in video image data, and then drives the organ in a corresponding three-dimensional facial model according to the preset organ driving rule, thereby achieving more vivid animation effect; and the method avoids animation effect deviation caused by the movement detection errors of a single organ characteristic point when the prior art adopts single organ driving.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a video-based three-dimensional facial animation driving method and system. Background technique [0002] The 3D facial animation technology started in the 1970s, and subsequent researchers have done a lot of work in order to generate realistic and vivid 3D facial animation. The current further research direction is that people hope to simulate various expressions and actions of real faces in real time, but due to the complexity of the physiological structure of the face itself and people's sensitivity to the appearance of the face, it is difficult to achieve this goal. very difficult. [0003] A simple implementation method is to drive the face organs in the 3D face model by detecting the changes of the feature points of the face organs in the video data, so as to achieve the animation effect of real-time simulation. For example, Logitech's products already on the mar...

AI Technical Summary

Problems solved by technology

[0005] However, because the core idea of ​​the above-mentioned prior art is to drive the facial organs of the three-dimensional human face model by tracking the changes of the feature points of each organ, and then achieve animation effects; and in practical applications, due to processing speed and computational difficulty The limitation of the above-mentioned existing technology makes the actual animation effect that can be achieved by the above-mentioned prior art relatively simple and not realistic enough. For example, for the driving of the mouth, only simple opening and closing of the mouth can be realized, and the driving of the eyebrows can only be realized simply. eyebrow up and down movement

[0006] Based on the above description of the specific processing process, it is easy to see that the existing solutions can only simply complete the corresponding drive of a single organ, which is very mechanical and difficult to achieve a more realistic and realistic 3D facial animation

Images