We present MocapNET, 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 ensembl…
demo real-time computer-vision neural-network tensorflow ensemble mocap bvh webcam gesture-recognition pose-estimation 3d-animation 3d-pose-estimation 2d-to-3d bvh-format rgb-images
-
Updated
Sep 26, 2024 - C++