Three-dimensional virtual character action complementing method and device and server

Abstract

The invention provides a three-dimensional virtual character action completion method, which comprises the following steps of: preprocessing and splicing data of a past frame and a target frame of action data to be completed to generate an input vector, inputting the input vector into a trained action completion neural network model to obtain prediction data, calculating current transition frame data according to the prediction data, processing and splicing current transition frame data to generate an input vector, inputting the input vector into the trained action complementation neural network model again to obtain prediction data, calculating next transition frame data according to the prediction data, and obtaining data of all transition frames according to the method. The method is suitable for scenes which are long in generation time, large in number of transition frames and complex in action, the generated transition frames are real in action, the labor cost needed by an original interpolation scheme is reduced, the project quality is improved, and the project period is shortened. The invention further provides a three-dimensional virtual character action complementing device, a server and a computer readable storage medium which all have the above beneficial effects.

Description

Technical field [0001] The present application relates to the field of role animation actions and editing technology, and in particular, there is a three-dimensional virtual role actions to make up a full method, a three-dimensional virtual role actions, and a full-tuning device, a server, and a computer readable storage medium. Background technique [0002] In three-dimensional animations or games, the three-dimensional virtual image is driven by animation data, forming various actions such as walking, running, jumping, and dance. Animation data can be created by animation or by action capture device. The animation data captured by the action capture device has not been used directly, often in some unsatisfactory action fragments, also needs to be modified by an animator. Therefore, in these two situations, there is a need for artists' manual editing. [0003] When the animator uses movie software, you will edit or modify several keyframes, and specify several keyframes related ...

AI Technical Summary

Problems solved by technology

However, this method is only suitable for action transitions with short generation time, few transition frames, and simple actions

However, in the actual production process, an animator has to edit or modify a large number of key frames. If the number of key frames is too small, the time interval is too short, or the action is too complicated, the interpolation method will get an unreal and unreasonable transition sequence.

Using the existing solution will rely heavily on the skills and experience of the animators, thereby increasing the labor cost; due to the unreasonable transition sequences that are prone to occur, and the uneven technical level of the animators and other personnel, the quality of the project will also be affected ; At the same time, due to the need to debug and edit a large number of keyframes, it will greatly increase the project cycle

Images