Method for generating animation based on human face image, and calculating equipment

Abstract

The invention discloses a method for generating an animation based on a human face image, and the method comprises the steps: extracting human face feature points of the human face image; generating a human face three-dimensional model through the human face feature points and a first projection matrix corresponding to the human face three-dimensional model; calculating and obtaining a full-image three-dimensional grid model of the human face image through the human face three-dimensional model; calculating full-image texture coordinates according to the full-image three-dimensional grid model and the first projection matrix; generating a second projection matrix through modifying the parameters of the first projection matrix; carrying out the projection of the full-image three-dimensional grid model and the human face three-dimensional model through the first projection matrix and the second projection matrix, and generating an image after three-dimensional reconstruction; carrying out the texture mapping of the image through the full-image texture coordinates after three-dimensional reconstruction, and generating a processed image; sequentially carrying out the steps of parameter modifying, projection and texture mapping in a repeated manner, and obtaining a plurality of processed images; and generating an animation according to the plurality of processed images. The invention also provides calculating equipment executing the above method.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and computing device for generating animation based on a face image. Background technique [0002] In the process of daily shooting and socializing, users hope to make some dynamic adjustments to the faces in an image to increase the fun. [0003] Currently, the techniques for dynamically adjusting face images are mainly based on two-dimensional image processing transformation and three-dimensional face model reconstruction. Only the processing on two-dimensional images often has problems such as facial distortion and strong sense of plane, so more and more technologies use methods based on three-dimensional face model reconstruction. The existing 3D face model reconstruction technology is mainly based on the linear combination of 3D face model data. The combination parameters are obtained through the projection matching of the 2D face and the corresponding 3D ...

AI Technical Summary

Problems solved by technology

However, the existing 3D face model reconstruction technology only considers the face area more, and ignores other non-face areas, such as hair, neck, shoulders and other body parts, and often only deducts the face area for processing. The non-face background area adopts a constant processing scheme, so that when the dynamically processed image is synthesized, the non-face part background area and the face area cannot be well blended

Especially when multiple such dynamically processed images are used to form a video, it is difficult to achieve an overall natural and smooth animation effect

Images