eos: A lightweight header-only 3D Morphable Face Model fitting library in modern C++11/14.
eos is a lightweight 3D Morphable Face Model fitting library that provides just the bare minimum to load a model and perform camera and shape fitting. It's written in modern C++11/14.
At the moment, it mainly provides the following functionality:
- MorphableModel class to represent a 3DMM (using OpenCVs
cv::Mat
) - Our low-resolution, shape-only 3D Morphable Face Model (share/sfm_shape_3448.bin)
- A linear scaled orthographic projection camera pose estimation algorithm
- Shape fitting, implementation of the linear shape-to-landmarks fitting of O. Aldrian & W. Smith, Inverse Rendering of Faces with a 3D Morphable Model, PAMI 2013
- Expression fitting, and 6 linear expression blendshapes: anger, disgust, fear, happiness, sadness, surprise.
- Isomap texture extraction to obtain a pose-invariant representation of the face texture.
- (Experimental): Non-linear fitting cost functions using Ceres for shape, camera, blendshapes and the colour model (needs Ceres to be installed separately)
- (New, experimental): Python bindings for parts of the library
Usage
- Tested with the following compilers: >=gcc-4.8.4, >=clang-3.5, Visual Studio 2015
- Needed dependencies for the library: Boost system (>=1.50.0), OpenCV core (>=2.4.3)
To use the library in your own project, just add the following directories to your include path:
eos/include
eos/3rdparty/cereal-1.1.1/include
eos/3rdparty/glm
Make sure to clone with --recursive
to download the required submodules!
Build the examples and tests
- Needed dependencies for the example app: CMake (>=2.8.10), Boost system, filesystem, program_options (>=1.50.0), OpenCV core, imgproc, highgui (>=2.4.3).
To build:
git clone --recursive https://github.com/patrikhuber/eos.git
mkdir build && cd build # creates a build directory next to the _eos_ folder
cmake -G "<your favourite generator>" ../eos -DCMAKE_INSTALL_PREFIX=../install/
make && make install # or open the project file and build in an IDE like Visual Studio
If some dependencies can't be found, copy initial_cache.cmake.template
to initial_cache.cmake
, edit the necessary paths and run cmake
with -C ../eos/initial_cache.cmake
.
Sample code
The fit-model example app creates a 3D face from a 2D image.
After make install
or running the INSTALL
target, an example image with landmarks can be found in install/bin/data/
. The model and the necessary landmarks mapping file are installed to install/share/
.
You can run the example just by running:
fit-model
Or, by manually specifying the face model, landmark-to-vertex mappings, an image and its 2D landmarks:
fit-model -m ../share/sfm_shape_3448.bin -p ../share/ibug2did.txt -i data/image_0010.png -l data/image_0010.pts
The output is an obj
file with the shape and a png
with the extracted isomap. The estimated pose angles and shape coefficients are available in the code via the API.
See examples/fit-model.cpp for the full code.
The Surrey Face Model
The library includes a low-resolution shape-only version of the Surrey Morphable Face Model. It is a PCA model of shape variation built from 3D face scans. It comes with uv-coordinates to perform texture remapping.
The full model is available at http://www.cvssp.org/facemodel.
Python bindings
Experimental: eos includes python bindings for some of its functionality (and more can be added!). Set -DBUILD_UTILS=on
and -DGENERATE_PYTHON_BINDINGS=on
when running cmake
to build them (and optionally set PYTHON_EXECUTABLE
to point to your python interpreter if it's not found automatically).
After building the bindings, they can be used like any python module:
import eos
import numpy as np
model = eos.morphablemodel.load_model("eos/share/sfm_shape_3440.bin")
s = model.get_shape_model().draw_sample([1.0, -0.5, 0.7])
sample = np.array(s) # the conversion from 'Mat' to a numpy array is necessary at the moment
help(eos) # check the documentation
Documentation
Doxygen: http://patrikhuber.github.io/eos/doc/
The fit-model example and the Namespace List in doxygen are a good place to start.
License & contributions
This code is licensed under the Apache License, Version 2.0. The 3D morphable face model under share/sfm_shape_3448.bin is free for use for non-commercial purposes. For commercial purposes and to obtain other model resolutions, see http://www.cvssp.org/facemodel.
Contributions are very welcome! (best in the form of pull requests.) Please use GitHub issues for any bug reports, ideas, and discussions.
If you use this code in your own work, please cite the following paper: A Multiresolution 3D Morphable Face Model and Fitting Framework, P. Huber, G. Hu, R. Tena, P. Mortazavian, W. Koppen, W. Christmas, M. Rätsch, J. Kittler, International Conference on Computer Vision Theory and Applications (VISAPP) 2016, Rome, Italy PDF(http://www.patrikhuber.ch/files/3DMM_Framework_VISAPP_2016.pdf).