Surface Reconstruction based on Self-Merging Octree with Deep Learning

A model segment method called Octree Subdivision has been presented for long years, which allows any three-dimensional point cloud object to be subdivided into infinitesimals so that it can be approximated by a particular surface function. In this paper, we proposed a new method named self-merging octree to reconstruct the surface of 3D Point Cloud which can be obtained by laser scanners or generated by some 3D modeling software. Different from any other surface reconstruction algorithms such as local property-based or specific type-based, a function pool-based was introduced in our research because it can express many different types of surfaces. We subdivide point cloud model by self-merging octree and categorize it by the neuro-network. In this idea, it is easy for us to find a proper surface function to present the subsurface of the model. What‘s more, while we extend the function pool, we can indicate far more style models. We have tried to reconstruct many point cloud models‘ surfaces in this way, and it works well and also shows its potential ability to build a bridge in the fields of model editing, model splicing, and model deformation.

[1]  Lexing Ying,et al.  A simple manifold-based construction of surfaces of arbitrary smoothness , 2004, ACM Trans. Graph..

[2]  C. Grimm.  Simple manifolds for surface modeling and parameterization , 2002, Proceedings SMI. Shape Modeling International 2002.

[3]  Ligang Liu,et al.  Manifold Construction Over Polyhedral Mesh , 2017 .

[4]  John F. Hughes,et al.  Modeling surfaces of arbitrary topology using manifolds , 1995, SIGGRAPH.

[5]  Josep Cotrina Navau,et al.  Modeling surfaces from meshes of arbitrary topology , 2000, Comput. Aided Geom. Des..

[6]  C. Qi.  Deep Learning on Point Sets for 3 D Classification and Segmentation , 2016 .

[7]  Hong Qin,et al.  Polycube splines , 2007, Comput. Aided Des..

[8]  Yang Liu,et al.  Adaptive O-CNN , 2018, ACM Trans. Graph..

[9]  Jianping Hu,et al.  Multi-scale geometry detail recovery on surfaces via Empirical Mode Decomposition , 2018, Comput. Graph..

[10]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[11]  Hong Qin,et al.  Manifold T-Spline , 2006, GMP.

[12]  Hong Qin,et al.  Manifold splines with single extraordinary point , 2007, Comput. Aided Des..

[13]  Yang Liu,et al.  O-CNN , 2017, ACM Trans. Graph..

[14]  Ligang Liu,et al.  Construction of Manifolds via Compatible Sparse Representations , 2016, ACM Trans. Graph..

[15]  Donald Meagher,et al.  Geometric modeling using octree encoding , 1982, Computer Graphics and Image Processing.

[16]  Bert Jüttler,et al.  Piecewise Rational Manifold Surfaces with Sharp Features , 2009, IMA Conference on the Mathematics of Surfaces.

[17]  Hong Qin,et al.  Manifold splines , 2005, SPM '05.

[18]  Chenglu Wen,et al.  Patch-Based Semantic Labeling of Road Scene Using Colorized Mobile LiDAR Point Clouds , 2016, IEEE Transactions on Intelligent Transportation Systems.

[19]  Wenping Wang,et al.  Feature-preserving T-mesh construction using skeleton-based polycubes , 2015, Comput. Aided Des..