3D Non-rigid Registration of Deformable Object Using GPU

We propose a method to quickly process non-rigid registration between 3D deformable data using a GPU-based non-rigid ICP(Iterative Closest Point) algorithm. In this paper, we sequentially acquire whole-body model data of a person moving dynamically from a single RGBD camera. We use Dense Optical Flow algorithm to find the corresponding pixels between two consecutive frames. Next, we select nodes to estimate 3D deformation matrices by uniform sampling algorithm. We use a GPU-based non-rigid ICP algorithm to estimate the 3D transformation matrices of each node at high speed. We use non-linear optimization algorithm methods in the non-rigid ICP algorithm. We define energy functions for an estimate the exact 3D transformation matrices. We use a proposed GPU-based method because it takes a lot of computation time to calculate the 3D transformation matrices of all nodes. We apply a 3D transformation to all points with a weight-based affine transformation algorithm. We demonstrate the high accuracy of non-rigid registration and the fast runtime of the non-rigid ICP algorithm through experimental results.

[1]  Dieter Fox,et al.  DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[3]  Ming Zeng,et al.  Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[5]  T. Dahlin,et al.  A comparison of the Gauss-Newton and quasi-Newton methods in resistivity imaging inversion , 2002 .

[6]  Richard Szeliski,et al.  Matching 3-D anatomical surfaces with non-rigid deformations using octree-splines , 1993, Proceedings of IEEE Workshop on Biomedical Image Analysis.

[7]  Qionghai Dai,et al.  Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization , 2015, ICCV.

[8]  Kun Li,et al.  Robust Non-Rigid Registration with Reweighted Position and Transformation Sparsity , 2019, IEEE Transactions on Visualization and Computer Graphics.

[9]  M. Pauly,et al.  Embedded deformation for shape manipulation , 2007, SIGGRAPH 2007.

[10]  Yongtian Wang,et al.  Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Alberto Signoroni,et al.  Deformable registration using patch-wise shape matching , 2014, Graph. Model..

[12]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[13]  Sridha Sridharan,et al.  Non-rigid Reconstruction with a Single Moving RGB-D Camera , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[14]  Zhiyi Yang,et al.  Parallel Image Processing Based on CUDA , 2008, 2008 International Conference on Computer Science and Software Engineering.

[15]  Andrew W. Fitzgibbon,et al.  Real-time non-rigid reconstruction using an RGB-D camera , 2014, ACM Trans. Graph..

[16]  Pushmeet Kohli,et al.  Fusion4D , 2016, ACM Trans. Graph..

[17]  Christopher Zach,et al.  Robust Bundle Adjustment Revisited , 2014, ECCV.

[18]  H. Hartley.  The Modified Gauss-Newton Method for the Fitting of Non-Linear Regression Functions by Least Squares , 1961 .

[19]  Slobodan Ilic,et al.  SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.