Golyanik V. Robust Methods for Dense Monocular Non-Rigid 3D Reconstruction and Alignment of Point Clouds

Springer, 2020. — 369 p. — ISBN: 978-3-658-30566-6.Vladislav Golyanik proposes several new methods for dense non-rigid structure from motion (NRSfM) as well as alignment of point clouds. The introduced methods improve the state of the art in various aspects, i.e. in the ability to handle inaccurate point tracks and 3D data with contaminations. NRSfM with shape priors obtained on-the-fly from several unoccluded frames of the sequence and the new gravitational class of methods for point set alignment represent the primary contributions of this book.Preliminaries
Review of Previous Work
Scalable Dense Non-Rigid Structure from Motion
Shape Priors in Dense Non-Rigid Structure from Motion
Coherent Depth Fields with High Dimensional Space Model
Monocular Non-Rigid Surface Reconstruction with Learned Deformation Model
Probabilistic Point Set Registration with Prior Correspondences
Point Set Registration Relying on Principles of Particle Dynamics
Application of Point Set Registration and Monocular Non-Rigid 3D Reconstruction to Scene Flow Estimation
Summary, Conclusions and Outlook