Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboids

Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

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

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

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

[4]  Luc Van Gool,et al.  RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Atilla Baskurt,et al.  Segmentation and Superquadric Modeling of 3D Objects , 2003, WSCG.

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

[7]  Jun Li,et al.  Im2Struct: Recovering 3D Shape Structure from a Single RGB Image , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[9]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[10]  David H. Laidlaw,et al.  Constructive solid geometry for polyhedral objects , 1986, SIGGRAPH.

[11]  Robert B. Fisher,et al.  Equal-Distance Sampling of Supercllipse Models , 1995, BMVC.

[12]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[13]  Dimitris N. Metaxas,et al.  Dynamic 3D models with local and global deformations: deformable superquadrics , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[14]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[15]  Lu Fang,et al.  SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[17]  Tao Mei,et al.  Concurrent Multiple Instance Learning for Image Categorization , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Mathieu Aubry,et al.  AtlasNet: A Papier-M\^ach\'e Approach to Learning 3D Surface Generation , 2018, CVPR 2018.

[19]  Long Quan,et al.  MVSNet: Depth Inference for Unstructured Multi-view Stereo , 2018, ECCV.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[23]  Ruzena Bajcsy,et al.  Recovery of Parametric Models from Range Images: The Case for Superquadrics with Global Deformations , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Armando Solar-Lezama,et al.  Learning to Infer Graphics Programs from Hand-Drawn Images , 2017, NeurIPS.

[25]  Subhransu Maji,et al.  CSGNet: Neural Shape Parser for Constructive Solid Geometry , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Leonidas J. Guibas,et al.  Learning Shape Abstractions by Assembling Volumetric Primitives , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Alex Pentland,et al.  Parts: Structured Descriptions of Shape , 1986, AAAI.

[28]  Franc Solina.  Volumetric models in computer vision—an overview , 1994 .

[29]  Narendra Ahuja,et al.  DeepMVS: Learning Multi-view Stereopsis , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[30]  Silvio Savarese,et al.  3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction , 2016, ECCV.

[31]  Jitendra Malik,et al.  Hierarchical Surface Prediction for 3D Object Reconstruction , 2017, 2017 International Conference on 3D Vision (3DV).

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

[33]  Max Jaderberg,et al.  Unsupervised Learning of 3D Structure from Images , 2016, NIPS.

[34]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[35]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[36]  Luc Van Gool,et al.  Learned Multi-patch Similarity , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Yiyi Liao,et al.  Deep Marching Cubes: Learning Explicit Surface Representations , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Thomas Brox,et al.  Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[39]  Cordelia Schmid,et al.  Learning from Synthetic Humans , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Andreas Birk,et al.  Revisiting Superquadric Fitting: A Numerically Stable Formulation , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  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).