search

patrikhuber / superviseddescent

C++11 implementation of the supervised descent optimisation method
http://patrikhuber.github.io/superviseddescent/
Apache License 2.0
402 stars 188 forks source link

Purpose of post estimation and simple function in superviseddescent #4

Closed wiliamc closed 9 years ago

wiliamc commented 9 years ago

Hi Patrik,

I builded the code and generated executable files for landmarkdetection, poseestimation and simplefunction

Can you please tell me the usage of poseestimation.cpp and simplefunction.cpp and how to execute the files

Landmark Detection: I gave the inputs and got the output with some points drawn on the image.

Pose Estimation: when i run these, getting residual points alone

For, Simple function no idea about that.

patrikhuber commented 9 years ago

Hi cibin91,

I strongly suggest you read the paper by the original authors, Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision. As you can read in the README.md, the library implements a learning-based approach to certain vision (and possibly other) problems. One of the most popular use cases is facial landmark detection. The examples provided are deliberately short "hello world" examples. If you're interested in landmark detection, I'm in the process of making our full pre-trained model available.

Another application where we use a setup a bit similar to the pose estimation example given here is described in our paper Fitting 3D Morphable Models using Local Features.

I think in your case, you first need to think about what you want to do, and then start from there.

Hope that helps,

Patrik

patrikhuber commented 9 years ago

I'm going to close this, as the documentation and the paper should explain most. Feel free to come back with any specific questions or problems.

If you're just interested in running landmark detection, have a look at my latest post in #3.