Header logo is

Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image

2020

Conference Paper

avg


Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural networks (CNNs) demonstrated impressive progress in 3D reconstruction, even when using a single 2D image as input. However, the majority of these methods focuses on recovering the local 3D geometry of an object without considering its part-based decomposition or relations between parts. We address this challenging problem by proposing a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives as well as their latent hierarchical structure without part-level supervision. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives, where simple parts are represented with fewer primitives and more complex parts are modeled with more components. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.

Author(s): Despoina Paschalidou and Luc Gool and Andreas Geiger
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2020

Department(s): Autonomous Vision
Bibtex Type: Conference Paper (inproceedings)

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020
Event Place: Seattle, USA

Links: pdf
suppmat
Video 2
Project Page
Slides
Poster
Video 1
Video:
Video:

BibTex

@inproceedings{Paschalidou2020CVPR,
  title = {Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image},
  author = {Paschalidou, Despoina and Gool, Luc and Geiger, Andreas},
  booktitle = { Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
  doi = {}
}