A conditional generative adversarial network three-dimensional facial expression motion unit synthesis method

Abstract

The invention relates to the field of man-machine emotion interaction, intelligent robots and the like, and aims to provide a corresponding solution way for researching generation and control problemsof natural facial expressions of a humanoid robot by taking a three-dimensional face model oriented to a virtual or entity humanoid robot as a carrier. Therefore, the conditional generative adversarial network three-dimensional facial expression motion unit synthesis method comprises the following steps: (1) establishing effective mapping between facial motion unit labels with different intensities and different combinations and facial expression parameter distribution; (2) carrying out game optimization on the generation result of the expression motion parameter generation model; And (3) applying the generated target expression parameters to the three-dimensional face model facing the humanoid robot to realize generation and control of the three-dimensional face complex expression of thehumanoid robot. The method is mainly applied to intelligent robot design and manufacturing occasions.

Description

technical field [0001] The present invention relates to the fields of human-computer emotional interaction and intelligent robots, and in particular to a method for synthesizing three-dimensional facial expression motion units based on Conditional Generative Adversarial Network (CGAN) and three-dimensional morphable model (3D MorphableModel, 3DMM). The method can be widely used in scenes such as facial expression control of humanoid intelligent robots, game animation and other 3D facial expression synthesis and human-computer emotional interaction. Background technique [0002] As an important goal of future robot development, humanoid robots with natural expression interaction have attracted extensive attention from academia and business circles. The natural expression interaction process generally includes two aspects: expression recognition and expression generation. Due to the diversity of facial expressions and the complexity of hardware design of humanoid robots, how t...

AI Technical Summary

Problems solved by technology

Although the existing methods have made some progress in AU labeling, but because facial AU labeling is very complex and is easily affected by different face shapes, different expressions, different lighting and facial postures, facial expression movement for humanoid robots based on AU labeling Unit synthesis still faces many challenges and difficulties, and it is difficult to be widely used

Images