Sparse Non-rigid Registration of 3D Shapes

Jingyu Yang Tianjin University, China Ke Li Tianjin University, China Kun Li Tianjin University, China Yu-Kun Lai Cardiff University, UK

Geometric Modeling and Processing mathscidoc:1608.16084

Computer Graphics Forum, 34, (5), 89-99, 2015
Non-rigid registration of 3D shapes is an essential task of increasing importance as commodity depth sensors become more widely available for scanning dynamic scenes. Non-rigid registration is much more challenging than rigid registration as it estimates a set of local transformations instead of a single global transformation, and hence is prone to the overfitting issue due to underdetermination. The common wisdom in previous methods is to impose an l2-norm regularization on the local transformation differences. However, the l2-norm regularization tends to bias the solution towards outliers and noise with heavy-tailed distribution, which is verified by the poor goodness- of-fit of the Gaussian distribution over transformation differences. On the contrary, Laplacian distribution fits well with the transformation differences, suggesting the use of a sparsity prior. We propose a sparse non-rigid registration (SNR) method with an l1-norm regularized model for transformation estimation, which is effectively solved by an alternate direction method (ADM) under the augmented Lagrangian framework. We also devise a multi-resolution scheme for robust and progressive registration. Results on both public datasets and our scanned datasets show the superiority of our method, particularly in handling large-scale deformations as well as outliers and noise.
No keywords uploaded!
[ Download ] [ 2016-08-28 01:42:58 uploaded by yukunlai ] [ 1744 downloads ] [ 0 comments ] [ Cited by 3 ]
@inproceedings{jingyu2015sparse,
  title={Sparse Non-rigid Registration of 3D Shapes},
  author={Jingyu Yang, Ke Li, Kun Li, and Yu-Kun Lai},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160828014258885549467},
  booktitle={Computer Graphics Forum},
  volume={34},
  number={5},
  pages={89-99},
  year={2015},
}
Jingyu Yang, Ke Li, Kun Li, and Yu-Kun Lai. Sparse Non-rigid Registration of 3D Shapes. 2015. Vol. 34. In Computer Graphics Forum. pp.89-99. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20160828014258885549467.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved