I writing the this video process app which requires the each video frame to be processed such that parts of the video are enlarged. As a reference, one of the snapchat lens filter enlarges the eyes of a person in the video. This is the exact effect I want to achieve.
How can I achieve this effect?
Update:
I have attached an example of eye enlargement from the web.
The answer is surprisingly simple: You move the vertices of the face-geometry.
To elaborate, the white wireframe mesh on the left of your image is placed so the geometry aligns with the photo. It is then texture-mapped with the photo, meaning that for each vertex in the mesh, a texture-coordinate is assigned (the point on the photo that should map to the vertex).
With every vertex assigned a texture-coordinate you can deform the mesh, doing ordinary texture-sampling at the interpolated texture-coordinates to have the image stretch - as if it was painted onto the head.
If you need to do this in realtime, you can use your graphics-card to do this; texture mapping is one of the things GPUs are really good at.
Now, if you want to do this on a video, you need to track the facial features to continuously align the geometry to the video. This is not an easy task, but you can probably find a wealth of libraries to help you out.
I am a bit uncertain which of the above would be difficult, so please feel free to ask any questions.
In a post processing step instead of sampling the origin pixel directly from where the target pixel is you instead sample the origin pixel slightly offset.
Where you get the offset can differ. For example you could provide an extra texture with the offsets encoded in the red and green channels.
