Learning Part Generation and Assembly for Structure-aware Shape Synthesis

Learning powerful deep generative models for 3D shape synthesis is largely hindered by the difficulty in ensuring plausibility encompassing correct topology and reasonable geometry. Indeed, learning the distribution of plausible 3D shapes seems a daunting task for the holistic approaches, given the significant topological variations of 3D objects even within the same category. Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet. The network is composed of an array of per-part VAE-GANs, generating semantic parts composing a complete shape, followed by a part assembly module that estimates a transformation for each part to correlate and assemble them into a plausible structure. Through delegating the learning of part composition and part placement into separate networks, the difficulty of modeling structural variations of 3D shapes is greatly reduced. We demonstrate through both qualitative and quantitative evaluations that PAGENet generates 3D shapes with plausible, diverse and detailed structure, and show two applications, i.e., semantic shape segmentation and part-based shape editing.

[1]  Hans-Peter Seidel,et al.  Pattern-aware shape deformation using sliding dockers , 2011, ACM Trans. Graph..

[2]  Mathieu Aubry,et al.  A Papier-Mache Approach to Learning 3D Surface Generation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Frédéric Maire,et al.  Learning Free-Form Deformations for 3D Object Reconstruction , 2018, ACCV.

[4]  Zoran Popovic,et al.  The space of human body shapes: reconstruction and parameterization from range scans , 2003, ACM Trans. Graph..

[5]  Niloy J. Mitra,et al.  ShapeSynth: Parameterizing model collections for coupled shape exploration and synthesis , 2014, Comput. Graph. Forum.

[6]  Daniel Cohen-Or,et al.  Component‐wise Controllers for Structure‐Preserving Shape Manipulation , 2011, Comput. Graph. Forum.

[7]  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 .

[8]  Leonidas J. Guibas,et al.  GRASS: Generative Recursive Autoencoders for Shape Structures , 2017, ACM Trans. Graph..

[9]  Leonidas J. Guibas,et al.  A scalable active framework for region annotation in 3D shape collections , 2016, ACM Trans. Graph..

[10]  Dani Lischinski,et al.  SAGNet , 2018, ACM Trans. Graph..

[11]  Daniel Cohen-Or,et al.  Learning to Generate the "Unseen" via Part Synthesis and Composition , 2018, ArXiv.

[12]  Hao Zhang,et al.  Learning Implicit Fields for Generative Shape Modeling , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

[14]  Vladimir G. Kim,et al.  Data‐Driven Shape Analysis and Processing , 2015, Comput. Graph. Forum.

[15]  Kun Liu,et al.  PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Szymon Rusinkiewicz,et al.  Modeling by example , 2004, SIGGRAPH 2004.

[17]  Leonidas J. Guibas,et al.  Learning Representations and Generative Models for 3D Point Clouds , 2017, ICML.

[18]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Leonidas J. Guibas,et al.  ShapeNet: An Information-Rich 3D Model Repository , 2015, ArXiv.

[20]  Leonidas J. Guibas,et al.  SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Ian D. Reid,et al.  Efficient Dense Point Cloud Object Reconstruction Using Deformation Vector Fields , 2018, ECCV.

[22]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[23]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[24]  Kun Zhou,et al.  Interactive images , 2012, ACM Trans. Graph..

[25]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[26]  Siddhartha Chaudhuri,et al.  SCORES: Shape Composition with Recursive Substructure Priors , 2018, ACM Trans. Graph..

[27]  Leonidas J. Guibas,et al.  Probabilistic reasoning for assembly-based 3D modeling , 2011, SIGGRAPH 2011.

[28]  Silvio Savarese,et al.  DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[29]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[30]  Leonidas J. Guibas,et al.  ComplementMe , 2017, ACM Trans. Graph..

[31]  N. Mitra,et al.  Exploration of continuous variability in collections of 3D shapes , 2011, SIGGRAPH 2011.

[32]  Hao Su,et al.  A Point Set Generation Network for 3D Object Reconstruction from a Single Image , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Daniel Cohen-Or,et al.  iWIRES: an analyze-and-edit approach to shape manipulation , 2009, ACM Trans. Graph..

[34]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[35]  Richard A. Newcombe,et al.  DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Niloy J. Mitra,et al.  Learning Semantic Deformation Flows with 3D Convolutional Networks , 2016, ECCV.

[37]  Daniel Cohen-Or,et al.  Meta-representation of shape families , 2014, ACM Trans. Graph..

[38]  Daniel Cohen-Or,et al.  Fit and diverse , 2012, ACM Trans. Graph..

[39]  Ersin Yumer,et al.  3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[40]  Daniel Cohen-Or,et al.  Global-to-local generative model for 3D shapes , 2018, ACM Trans. Graph..

[41]  Leonidas J. Guibas,et al.  Composite Shape Modeling via Latent Space Factorization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[42]  Gernot Riegler,et al.  OctNet: Learning Deep 3D Representations at High Resolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Leonidas J. Guibas,et al.  Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces , 2018, Comput. Graph. Forum.

[44]  Siddhartha Chaudhuri,et al.  A probabilistic model for component-based shape synthesis , 2012, ACM Trans. Graph..

[45]  Stephen DiVerdi,et al.  Learning part-based templates from large collections of 3D shapes , 2013, ACM Trans. Graph..

[46]  Leonidas J. Guibas,et al.  StructureNet , 2019, ACM Trans. Graph..

[47]  Christopher K. I. Williams,et al.  The shape variational autoencoder: A deep generative model of part‐segmented 3D objects , 2017, Comput. Graph. Forum.

[48]  Jiangping Wang,et al.  Structure-Aware Shape Synthesis , 2018, 2018 International Conference on 3D Vision (3DV).

[49]  Wei Liu,et al.  Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images , 2018, ECCV.

[50]  Abhinav Gupta,et al.  Learning a Predictable and Generative Vector Representation for Objects , 2016, ECCV.

[51]  Jiajun Wu,et al.  Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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