Non-rigid point cloud registration

Last updated on Nov 3, 2022

As final contribution of my PhD thesis, I developed a non-rigid point cloud registration method that was successfully used to remove the motion distortion of 3D scans acquired with our underwater laser scanner.

I presented this work at IROS22:

Miguel Castillón
Miguel Castillón
Autonomous Navigation Lead

My main research interests include exploiting sensor perception for autonomous navigation and manipulation in challenging scenarios.

Publications

Linewise Non-Rigid Point Cloud Registration
During my research stay at ASL Zurich I developed a non-rigid point cloud registration method. You can check out the source code in this public repository.
Miguel Castillón, Pere Ridao, Roland Siegwart, César Cadena
Linewise Non-Rigid Point Cloud Registration