Method for synthesizing three-dimensional human motion by using recurrent neural network based on hierarchical learning

Abstract

The invention provides a method for synthesizing three-dimensional human motion by using a recurrent neural network based on hierarchical learning. The method comprises a model training step and a model testing step, the model training step comprises the following sub-steps: constructing a low-layer motion information extraction network by adopting a GRU unit; establishing a high-level motion synthesis network by adopting a GRU network; adopting motion data with different styles as input of a high-level motion synthesis network, combining the skeleton features of the motion data with the motion features extracted by the low-level motion information extraction network as input, and training the high-level motion synthesis network to learn skeleton space-time relationship information of motions with different styles; and inputting the first 30 frames of data of the motion data in the test set into the trained high-level motion synthesis network, and finally performing verification. The method not only can be used for synthesizing the motion conforming to the input track, but also can be used for generating the transition motion between two different types of motions, and can also beused for synthesizing motion sequences with different emotion styles.

Description

technical field [0001] The present invention relates to the technical fields of computer graphics and human motion modeling, in particular, to a method for synthesizing three-dimensional human motion using a cyclic neural network based on layered learning. Background technique [0002] Three-dimensional human body motion capture equipment is a high-tech device used to accurately measure the movement of human body in three-dimensional space. Based on methods such as multi-eye video and computer graphics, it can accurately obtain the 3D data of the joint points of the moving human body, and then reconstruct the human body motion data set based on the topological structure of the human body. This data set has a wide range of application values ​​and can be widely used in fields related to human motion analysis such as computer animation, virtual reality, security monitoring, and human-robot interaction. On the other hand, the reusability of human motion data is limited due to ...

AI Technical Summary

Problems solved by technology

Although optimization-based methods can synthesize motions that satisfy constraints, the modeling process is complex and it is difficult to handle large data sets

Although the method based on reinforcement learning can interact with the external environment, it is still limited by the complex modeling process and a single form of motion.

Images