Information processing method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses an information processing method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a target video, wherein each frame in the target video comprises a face image corresponding to a same object; inputting each frame of face image into a first target preset trunk model, and outputting a first target image feature; inputting the first target image feature into a first target preset network model, and correspondingly outputting a first target expression coefficient; wherein the first target preset network model is obtained by obtaining a shared identity coefficient and a shared texture coefficient and correspondingly performing expression coefficient prediction optimization training. The first target expression coefficient and the non-expression coefficient are decoupled, so that the accuracy of the extracted expression coefficient is greatly improved.

Description

technical field [0001] The present application relates to the field of computer vision technology, and in particular, to an information processing method, apparatus, computer equipment and storage medium. Background technique [0002] Face reconstruction is a popular direction in computer vision, and 3D face-related applications are also a new way of playing in the field of short videos in recent years. Among them, reconstructing face 3D models from face images is one of the basic technologies for many face-related applications. [0003] In the prior art, a 3D face model is usually constructed by a parametric face 3D reconstruction algorithm. The parametric face 3D reconstruction algorithm uses the media parameterized face 3D model as a priori information as a constraint, which will constrain the human face. The problem of face 3D reconstruction is transformed into the estimation of the parameters of the parametric face 3D model, which can well deal with the face 3D reconstr...

AI Technical Summary

Problems solved by technology

[0004] In order to implement subsequent operations such as speaker determination or expression editing, it is often necessary to extract the expression information of the face in the image. However, the 3DMM expression information directly extracted by the commonly used image-based parametric face 3D reconstruction algorithm will be combined with other non-expression information. Coupling makes the extracted expression information inaccurate and the accuracy of information processing is poor

Images