We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
This repository provides scripts that can be used to visualize BVH files. These scripts were developed for the GENEA Challenge 2020, and enables reproducing the visualizations used for the challenge stimuli. The server consists of several containers which are launched together with the docker-compose.
Yet Another Zombie Horror
Context
This engine is intended to be used as a drop-in replacement to Three.js’s
WebGLRenderer.Problem
It tends not to work as a drop-in replacement out-of-the-box, because the renderer crashes when:
THREE.Geometryinstead of aTHREE.BufferGeometry.This might cause people who try to repl