Upright Orientation of 3D Shapes with Convolutional Networks
- This is the test code for
Zishun Liu, Juyong Zhang, Ligang Liu. Upright Orientation of 3D Shapes with Convolutional Networks. Graphical Models, 85: 22-29, 2016.
- We have tested the code on Debian 8 and Matlab R2014b.
- If you have any questions, please contact Zishun Liu via firstname.lastname@example.org.
- The root folder contains a trained model and interfaces for testing. The regression network for four-legged/wheeled group in the paper is provided.
- The folder "data" contains several mesh files sampled from our test set, whose upright orientations are all positive z-axis.
- The folder "util" is for utilities such as mesh loading and random rotation generation.
- The folder "voxelization" is a toolbox to convert mesh models to their volume representations, from Jianxiong Xiao's Princeton Vision and Robotics Toolkit.
Compile the C-coded voxelization function in Matlab with
Edit the parameters in
main.mand run it in Matlab. The results like the following would be printed:
The prediction error is 2.7 degrees