superviseddescent
superviseddescent copied to clipboard
C++11 implementation of the supervised descent optimisation method
Hi Patrik, I see something that looks a bit strange to me: https://github.com/patrikhuber/superviseddescent/blob/0179b4b69e3bc6e2bfdae51f3169414444290d63/include/superviseddescent/regressors.hpp#L135 The lambda gets updated, but don't you want this method to be const and use a local...
Hi Patrick, I'd like to know if you think that the supervised descent method can be trained with 10000 images + landmarks? Do you have any advise to do so?...
also used the definition of the `VL_INLINE` macro from http://www.vlfeat.org/api/portability.html#host-compiler-other also, see #27
vl-hog has really good performance and it's hard to replace. But I don't like to include C headers and I would really like to replace it with a header-only, modern...
Hi Patrick, I'm trying to estimate different algorithm's tracking error. For that, I'm using two own databases; one with real faces (maybe you known [it](http://gi4e.unavarra.es/databases/hpdb/)) and other with synthetic faces...
The original SDM demo was released in Intraface project (Matlab and C++ versions) Comparing to Intraface, your implementation is not as robust and stable. Of course the reasons may be...
Doxygen has a @tparam command to document template parameters (https://www.stack.nl/~dimitri/doxygen/manual/commands.html#cmdtparam). We should probably use it in the library documentation.
At the moment, it prints `Failed to read 8 bytes from input stream! Read 0`, which is not that intuitive.
I'd like to support the popular _me17_ landmark set that's used in a lot of papers (e.g. [Zhou et al.](http://www.f-zhou.com/fa/2013_ICCV_EGM.pdf) and [ours](http://www.patrikhuber.ch/files/RCRC_SPL_2015.pdf)). However, some landmarks are different from the ibug-68...
`examples/landmark_detection` is a first-run example and it should run fairly quick to give the user some results. I should change it to only train 5 or 10 landmarks, so the...