Simple Python demos of Inverse Toon Shading [Xu et al. 2015].
Their main idea is using isophote, a contour of equal luminance. I would like to test each step of normal estimation process based on the isophote concept.
- Well-defined normals
- Intersecting isophotes
- Isophote normals
- 2D arc-length interpolation
- Integrating 2D tangent direction
- 3D projection
- Full normal field
- Diffuse isophote normals
- Project back to isophote constraint
Status: Under construction.
Note: This program was only tested on Windows with Python2.7. Linux and Mac OS are not officially supported, but the following instructions might be helpful for installing on those environments.
Please install the following required python modules.
- NumPy
- SciPy
- matplotlib
- OpenCV
- PyAMG
As these modules are heavily dependent on NumPy modules, please install appropriate packages for your development environment (Python versions, 32-bit or 64bit). For 64-bit Windows, you can download the binaries from Unofficial Windows Binaries for Python Extension Packages.
This program also uses docopt for CLI. docopt will be installed automatically through the following pip command for main modules.
Status: Under construction.
Status: Under construction.
API document will be managed by doxygen framework. Online version is provided in the following link:
- inversetoon API Document (html)
For a local copy, please use the following doxygen command from doxygen directory.
> doxygen doxygen_config
- Complete implementation.
- Update result section.
The MIT License 2015 (c) tody