2015 IEEE International Conference on Computer Vision (ICCV) (2015)
Dec. 7, 2015 to Dec. 13, 2015
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.236
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.
Optimization, Robustness, Distortion, Markov processes, Shape, Computational modeling, Labeling
Q. Chen and V. Koltun, "Robust Nonrigid Registration by Convex Optimization," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 2039-2047.