- Nov 15, 2016
-
-
Patrik Huber authored
-
- Nov 08, 2016
-
-
Patrik Huber authored
-
- Nov 07, 2016
-
-
Patrik Huber authored
-
Patrik Huber authored
-
- Sep 11, 2016
-
-
Patrik Huber authored
Changed all affected functions and classes accordingly: Mainly the renderer, affine-renderer, and affine texture extraction. This results in a ~35% speed-up of rendering meshes. It requires some not-so-beautiful conversions in render_affine and the current texture extraction, but they will be superseded by the new renderer soon anyway.
-
- Aug 22, 2016
-
-
Patrik Huber authored
Fits camera, shape, blendshapes and colour coefficients with a cost function containing a landmark constraint, priors, and minimising the error between the input image's RGB values and the model estimate (rendered at each vertex). Note: The image cost function cannot be used with the model on GitHub, as it doesn't include the colour PCA.
-
Patrik Huber authored
* Fits the pose (camera) to landmarks using the newly added Ceres cost functions * Added find_package(Ceres) to CMakeLists.txt
-
Patrik Huber authored
-
- May 22, 2016
-
-
Patrik Huber authored
-
- Apr 30, 2016
-
-
Patrik Huber authored
Added a BUILD_UTILS CMake option, defaulting to OFF.
-
- Feb 17, 2016
-
-
Patrik Huber authored
I don't think we need two representations for it, one struct with a type is easier. At the moment, we only use an orthographic camera anyway. - As before, it should contain all the parameters necessary to render an image using OpenGL, and conform to the OpenGL conventions - Updated all calling sites - Added serialisation - Added a convenience method to save the parameters to a json file
-
- Jan 16, 2016
-
-
Patrik Huber authored
Probably needed because OpenCV needs it, and we depend on OpenCV.
-
Patrik Huber authored
-
- Aug 23, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
fit-model: Replaced affine camera estimation with nonlinear algorithm (allows direct recovery of the pose angles)
-
Patrik Huber authored
This should make the app easier to understand, i.e. remove anything that's not necessary.
-
- Aug 15, 2015
-
-
MichaelGrupp authored
-
- Aug 14, 2015
-
-
MichaelGrupp authored
imread has moved from highgui to the imgcodecs module in version 3.0.
-
- Aug 11, 2015
-
-
MichaelGrupp authored
imread has moved from highgui to the imgcodecs module in version 3.0.
-
Patrik Huber authored
To facilitate this, added a get_texture_coordinates() method to MorphableModel
-
- Aug 02, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
Also updated the documentation of Mesh.
-
- Aug 01, 2015
-
-
patrikhuber authored
- We now use the same values and formulas as in Smith & Aldrian for the detector 2D variance. - This changes the ranges of values a bit, so set an equivalent reasonable regularisation default value
-
patrikhuber authored
Changed the detector variance in the shape fitting from clip-coords to image-coords. This makes the regularisation behave normal again. Also chose a slightly higher regularisation value to stay a bit closer to the mean face by default.
-
patrikhuber authored
-
patrikhuber authored
In the default setting, it links to OpenCV's debug libs, and that doesn't work with the STL of the RelWithDebInfo build.
-
patrikhuber authored
-
- Jul 31, 2015
-
-
patrikhuber authored
Also removed a few trailing whitespaces
-
- Jul 28, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
For path operator +=
-
- Jul 21, 2015
-
-
Patrik Huber authored
-
- Jul 12, 2015
-
-
Patrik Huber authored
-
- Jul 11, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
-
- Jul 09, 2015
-
-
Patrik Huber authored
-
- Jul 02, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
Removed all non-header-only CMake stuff and added a custom target for the library headers so they show up in IDEs
-
- Jun 30, 2015
-
-
Patrik Huber authored
-
Patrik Huber authored
-
Patrik Huber authored
-