Method for synthesizing three-dimensional human body movement based on non-linearity manifold study

Abstract

The present invention discloses a method for synthesizing three-dimensional human body movement based on non-linearity manifold study, so as to make three-dimensional human body movement animations, characterized in that firstly a set of sparse three-dimensional human body movement samples is mapped in movement semantic parameter space builded on a low-dimentsion manifold; then implementing uniformly distributed coarctation resample to the low dimensional movement semantic parameter space, and applying resample coefficient set to movement samples distributed in an original movement space sparsely to obtain dense and well distributed movement samples of a high dimensional space; then remapping the newly sampled high dimensional movement samples to obtain a final low dimensional movement semantic parameter space; finally, by means of interacting the movement semantic parameters synthezed selectively in the low dimensional semantic parameter space by users, the system maps the movement semantic parameter to a high dimensional movement space to obtain a new movement sequence. The invention is not only capable of controlling precisively movement physical parameters, e.g. movement position, physical movement characteristics of special arthrosis, and also used to synthesize novel movement data having high-rise movement semantion such as movement styles.

Description

technical field [0001] The invention relates to the field of computer three-dimensional animation, in particular to a three-dimensional human motion synthesis method based on nonlinear manifold learning. Background technique [0002] The existing data-driven motion synthesis technology provides many methods, such as motion transition, motion fusion, motion graph model, etc., so that users can use multiple existing motion data as input, and synthesize a new motion sequence through a series of algorithm processing . However, how to precisely control the result of motion synthesis has always been a difficulty faced by data-driven motion synthesis methods. The use of nonlinear manifold dimensionality reduction technology can explore the most essential motion characteristics of existing motion data, and can be used to guide the generation of motion data with new characteristics. However, many existing motion synthesis methods based on nonlinear manifold learning have the proble...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the data samples are loosely distributed in the low-dimensional space, and the semantics of the synthetic motion cannot be precisely controlled.

Images