Note to turn on the BUILD_PYTHON flag while building. OpenPose: See OpenPose offical installation.md for help.bvh_skeleton: This module includes the function that estimates skeleton information from 3D pose, converts 3D pose to joint angle and write motion data to bvh file.We slightly modificate the original implementation. VideoPose3D: This model is proposed by Dario Pavllo, Christoph Feichtenhofer, David Grangier, and Michael Auli in CVPR 2019.Its original implementation is based on TensorFlow, and we reimplemented it using PyTorch. 3d-pose-baseline: This model is proposed by Julieta Martinez, Rayat Hossain, Javier Romero, and James J.pose_estimator_3d: We provide 2 models to estimate 3D human pose.It can detect 2D joint keypoints accurately at real-time speed. pose_estimator_2d: Since the 3D pose estimation models we used are 2-stage model(image-> 2D pose -> 3D pose), this module is used for estimate 2D human pose (2D joint keypoint position) from image.Video2bvh consists of 3 modules: pose_estimator_2d, pose_estimator_3d and bvh_skeleton. Video2bvh extracts human motion in video and save it as bvh mocap file.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |