Robust Nonrigid Registration by Convex Optimization

Qifeng Chen Vladlen Koltun
IEEE International Conference on Computer Vision (ICCV), 2015





Abstract

We present an approach to nonrigid registration of 3D surfaces. We cast isometric embedding as MRF optimization and apply efficient global optimization algorithms based on linear programming relaxations. The Markov random field perspective suggests a natural connection with robust statistics and motivates robust forms of the intrinsic distortion functional. Our approach outperforms a large body of prior work by a significant margin, increasing registration precision on real data by a factor of 3.

Materials

Paper
Poster
Slide (PDF, PPT)
Complete code package (updated on 13 April 2016, 8.5 Gb)
Minimal code package (updated on 13 April 2016, 366 Mb)
Script to plot Figure 3