maxorange / pix2vox

Sketch-Based 3D Exploration with Stacked Generative Adversarial Networks

pix2vox

[Demonstration video]
Sketch-Based 3D Exploration with Stacked Generative Adversarial Networks.

Generated samples

Single-category generation

Multi-category generation

Requirements

The following python packages are required for running the application. If you are using anaconda, you can easily install VTK5 and PyQt4 (or they may already be installed).

• binvox-rw-py

• numpy

• scipy

• OpenCV

• TensorFlow (GPU support is recommended).

• VTK5

$ conda install -c anaconda vtk=5.10.1

• PyQt4

$ conda install -c anaconda pyqt=4.11.4

• QDarkStyleSheet

$ pip install qdarkstyle

Getting started

1. Install the python packages above
2. Install Git LSF (You need Git LSF to download trained model file)
3. Download the code from GitHub:

$ git lsf clone https://github.com/maxorange/pix2vox.git
$ cd pix2vox

4. Run the code:

$ python application.py