pix2vox

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

<img src="img/sample.gif" width="500">

Generated samples

Single-category generation

<img src="img/single-category-generation.png" width="500">

Multi-category generation

<img src="img/multi-category-generation.png" width="500">

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