search

twehrbein / Probabilistic-Monocular-3D-Human-Pose-Estimation-with-Normalizing-Flows

This is the official implementation of the ICCV 2021 Paper "Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows" by Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn and Bastian Wandt.
MIT License
68 stars 6 forks source link

MPI-INF-3DHP dataset #8

Open fsnelgar opened 5 months ago

fsnelgar commented 5 months ago

Thank you for you interesting work. Is it possible to also release the preprocessed data for the MPI-INF-3DHP dataset to allow fair comparison?

twehrbein commented 5 months ago

Hi, the annotations can be downloaded here: https://drive.google.com/file/d/1LJFw84Egv_sBRZlRvL2_BVOWI3ybMv1U/view?usp=sharing

Loading and preprocessing the annotations should be similar as done in data_h36m.py (except maybe reordering the joint ids to match the h36m skeleton). Unfortunately, I currently don't have the time to prepare the script myself.