Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Automatic Generator for Differentiable Minimal Solver
Minimal solvers are of extreme importance to robust geometric model estimation (e.g., relative camera pose). Automatic generators take a set of input constraints (usually polynomial) and automatically generate a solver that returns the sought model parameters given a set of input data points. None of the recent automatic generators account for the problem of creating differentiable minimal solvers - a problem that gets more and more attention with the success of deep learning-based methods.