FORTH Computational Vision and Robotics Laboratory

Repositories

• MocapNET

  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 ensemb…

  demo real-time computer-vision neural-network tensorflow ensemble mocap
  C++ 31 131 3 0 Updated Nov 18, 2020

• wacv_docker

  A Dockerfile for our WACV18 paper: Using a single RGB frame for real time 3D hand pose estimation in the wild.
  Dockerfile 0 0 0 0 Updated Oct 21, 2020

• PyOpenPose

  Python bindings for the Openpose library

  python wrapper python-bindings openpose
  Jupyter Notebook BSD-3-Clause 74 275 1 0 Updated Oct 16, 2020

• reading_group

  Reading group material and links
  0 8 0 0 Updated Feb 10, 2020

• MonocularRGB_3D_Handpose_WACV18

  Using a single RGB frame for real time 3D hand pose estimation in the wild
  Python 28 121 8 0 Updated Jun 4, 2019

• MonocularRGB_2D_Handjoints_MVA19

  Accurate Hand Keypoint Localization on Mobile Devices
  Python 9 63 5 0 Updated Apr 5, 2019

• HandTracker

  3D Hand Tracking using input from a depth sensor.
  Python 76 272 7 0 Updated May 5, 2017