wd-hub / multi-modal-regression

Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

multi-modal-regression

Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation

Please create the following folders: data, plots, results, models
I setup symbolic links in the data folder. For example: ln -s /path/to/rendered/data data/renderforcnn

If you encounter any problems, please contact me at siddharthm@jhu.edu.

If you use this work please cite our paper : A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Images Newer version of the work: Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks

About

Models and Loss functions for our Mixed Classification-Regression framework for 3D Pose Estimation

License:MIT License


Languages

Language:Python 90.8%Language:MATLAB 9.2%