A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]

Convert video to the bvh motion file

This repository contains an example script to convert from a SMPL model to a bvh file.

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.

➿A rerun plugin and tools for 3D animation

Hand Motion Capture from a 3D Leap Motion Controller for a Musculoskeletal Dynamic Simulation implemented in Python

BeeVeeH - another BVH Player + some BVH APIs

body25 + hand pose3d to bvh

Automatic motion generator from existing amc and asf files or bvh file

Celltree data structure for searching for points, lines, boxes, and cells (convex polygons) in a two dimensional unstructured mesh.

A simple BVH parser

Python utilities for reading and rendering Biovision Hierarchy skeleton and motion capture data

A Blender add-on for easy creation of proxy meshes for a selected armature object

Classification of movement types like walking, running using motion capture(BVH) file from CMU dataset.

ZBEAR's Drag N' Drop Importer v2.93

visualize BVH file skeletons using graphviz

Python module to import, parse and elaborate BVH files

A GPU-accelerated real-time mesh voxelizer in Python

A memory-efficient, realistic, real-time controllable locomotion generator.

High-Fidelity Skeleton-Aware Networks (HiFi SAN) reimagines the cycle-consistent Skeleton-Aware Network (Aberman et al.) by replacing its skeletal convolution layers with a Self-Attention mechanism (Transformer), showcasing improved performance of deep motion retargeting. HiFi SAN successfully retargets more complex skeletal data such as fingers.