Convolution-Based Design for Real-Time Pose Recognition and Character Animation Generation

Human pose recognition and its generation are an important animation design key point. To this end, this paper designs new neural network structures for 2D and 3D pose extraction tasks and corresponding GPU-oriented acceleration schemes. The scheme first takes an image as input, extracts the human pose from it, converts it into an abstract pose data structure, and then uses the converted dataset as a basis to generate the desired character animation based on the input at runtime. The scheme in this paper has been tested on pose recognition datasets and different levels of hardware showing that 2D pose recognition can reach speeds above 60 fps on common computer hardware, 3D pose recognition can be estimated to reach speeds above 24 fps with an average error of only 110 mm, and real-time animation generation can reach speeds above 30 frames per second.