Surface reconstruction with data-driven exemplar priors

In this paper, we propose a framework to reconstruct 3D models from raw scanned points by learning the prior knowledge of a specific class of objects. Unlike previous work that heuristically specifies particular regularities and defines parametric models, our shape priors are learned directly from existing 3D models under a framework based on affinity propagation. Given a database of 3D models within the same class of objects, we build a comprehensive library of 3D local shape priors. We then formulate the problem to select as-few-as-possible priors from the library, referred to as exemplar priors. These priors are sufficient to represent the 3D shapes of the whole class of objects from where they are generated. By manipulating these priors, we are able to reconstruct geometrically faithful models with the same class of objects from raw point clouds. Our framework can be easily generalized to reconstruct various categories of 3D objects that have more geometrically or topologically complex structures. Comprehensive experiments exhibit the power of our exemplar priors for gracefully solving several problems in 3D shape reconstruction such as preserving sharp features, recovering fine details and so on. We devise a framework for surface reconstruction from existing 3D models.Our framework is able to reconstruct various 3D objects without any interaction.We automatically learn the exemplar priors from a database of 3D shapes.Exemplar priors are able to represent the 3D shape of the whole class of objects.

[1]  Tony DeRose,et al.  Surface reconstruction from unorganized points , 1992, SIGGRAPH.

[2]  Frédo Durand,et al.  Non-iterative, feature-preserving mesh smoothing , 2003, ACM Trans. Graph..

[3]  Daniel Cohen-Or,et al.  Consolidation of unorganized point clouds for surface reconstruction , 2009, ACM Trans. Graph..

[4]  Sunghee Choi,et al.  A simple algorithm for homeomorphic surface reconstruction , 2000, SCG '00.

[5]  Sunghee Choi,et al.  The power crust, unions of balls, and the medial axis transform , 2001, Comput. Geom..

[6]  Hans-Peter Seidel,et al.  Feature-preserving non-local denoising of static and time-varying range data , 2007, Symposium on Solid and Physical Modeling.

[7]  Cláudio T. Silva,et al.  Robust Smooth Feature Extraction from Point Clouds , 2007, IEEE International Conference on Shape Modeling and Applications 2007 (SMI '07).

[8]  Daniel Cohen-Or,et al.  Non-local scan consolidation for 3D urban scenes , 2010, ACM Trans. Graph..

[9]  Tamal K. Dey,et al.  Detecting undersampling in surface reconstruction , 2001, SCG '01.

[10]  Leonidas J. Guibas,et al.  Data-driven structural priors for shape completion , 2015, ACM Trans. Graph..

[11]  Markus H. Gross,et al.  Feature Preserving Point Set Surfaces based on Non‐Linear Kernel Regression , 2009, Comput. Graph. Forum.

[12]  Gabriel Taubin,et al.  A benchmark for surface reconstruction , 2013, TOGS.

[13]  陈宝权 GlobFit: Consistently Fitting Primitives by Discovering Global Relations , 2011 .

[14]  Olga Sorkine-Hornung,et al.  Fast automatic skinning transformations , 2012, ACM Trans. Graph..

[15]  Philippe Bekaert,et al.  Self-similarity based compression of point set surfaces with application to ray tracing , 2008, Comput. Graph..

[16]  Sebastian Thrun,et al.  SCAPE: shape completion and animation of people , 2005, SIGGRAPH 2005.

[17]  Daniel Cohen-Or,et al.  Active co-analysis of a set of shapes , 2012, ACM Trans. Graph..

[18]  Daniel Cohen-Or,et al.  Surface reconstruction using local shape priors , 2007, Symposium on Geometry Processing.

[19]  M. Gross,et al.  Algebraic point set surfaces , 2007, SIGGRAPH 2007.

[20]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[21]  Daniel Cohen-Or,et al.  Parameterization-free projection for geometry reconstruction , 2007, ACM Trans. Graph..

[22]  Ron Kimmel,et al.  Patch‐Collaborative Spectral Point‐Cloud Denoising , 2013, Comput. Graph. Forum.

[23]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  Leonidas J. Guibas,et al.  Example-Based 3D Scan Completion , 2005 .

[25]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[26]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[27]  Reinhard Klein,et al.  Completion and Reconstruction with Primitive Shapes , 2009, Comput. Graph. Forum.

[28]  Delbert Dueck,et al.  Affinity Propagation: Clustering Data by Passing Messages , 2009 .

[29]  D. Levin,et al.  Mesh-Independent Surface Interpolation , 2004 .

[30]  M. Levoy,et al.  Gaussian KD-trees for fast high-dimensional filtering , 2009, SIGGRAPH 2009.

[31]  A. IMtech,et al.  Content-based Retrieval of 3 D Models : Feature Extraction and Representation Horace , 2005 .

[32]  Sunghee Choi,et al.  A Simple Algorithm for Homeomorphic Surface Reconstruction , 2002, Int. J. Comput. Geom. Appl..

[33]  DigneJulie,et al.  Self-similarity for accurate compression of point sampled surfaces , 2014 .

[34]  Junjie Cao,et al.  Deformation-driven topology-varying 3D shape correspondence , 2015, ACM Trans. Graph..

[35]  Hans-Peter Seidel,et al.  Smoothing by Example: Mesh Denoising by Averaging with Similarity-Based Weights , 2006, IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06).

[36]  Julie Digne,et al.  Similarity based filtering of point clouds , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[37]  Marc Alexa,et al.  Computing and Rendering Point Set Surfaces , 2003, IEEE Trans. Vis. Comput. Graph..

[38]  Tamy Boubekeur,et al.  Non Local Point Set Surfaces , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.

[39]  Jean-Daniel Boissonnat,et al.  Smooth surface reconstruction via natural neighbour interpolation of distance functions , 2002, Comput. Geom..

[40]  Alla Sheffer,et al.  Template-based mesh completion , 2005, SGP '05.

[41]  Evangelos Kalogerakis,et al.  Eurographics Symposium on Geometry Processing 2015 Analysis and Synthesis of 3d Shape Families via Deep-learned Generative Models of Surfaces , 2022 .

[42]  Thomas A. Funkhouser,et al.  A benchmark for 3D mesh segmentation , 2009, ACM Trans. Graph..

[43]  Alberto Del Bimbo,et al.  Content-based retrieval of 3D models , 2006, TOMCCAP.