Scalismo Lab: shape completion using Gaussian Process regression
In this hands-on step, we will focus on the shape completion part seen in the previous tutorial video and apply Gaussian Process regression to reconstruct Thomas Vetter’s missing nose.
We will start by extending the flexibility of our face model, built with a limited set of data, and augment it with a symmetrised Gaussian kernel.
Then, similar to the video, we will apply Gaussian Process regression and compute a posterior nose model yielding a normal distribution over probable nose reconstructions.
To access the tutorial document:
- Switch to Scalismo Lab.
- Select the Shape Completion Using Gaussian Process Regression document under:
Documents -> Fast track, for the fast track version
Documents -> Full track, for the full track version
If you have questions, ask them in the comments section here on FutureLearn.
If you are doing the full track version, please remember that the exercises are optional. If you find them too hard, you can continue going through the tutorial without solving the exercises.
© University of Basel