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

04/02/2020
by   Despoina Paschalidou, et al.
9

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.

READ FULL TEXT

page 13

page 14

page 15

page 23

page 26

03/18/2021

Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks

Impressive progress in 3D shape extraction led to representations that c...
08/01/2019

Automatic pre-grasps generation for unknown 3D objects

In this paper, the problem of automating the pre-grasps generation for n...
03/12/2019

Unsupervised Discovery of Parts, Structure, and Dynamics

Humans easily recognize object parts and their hierarchical structure by...
05/27/2020

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

This paper presents a fully automatic framework for extracting editable ...
04/16/2018

Im2Struct: Recovering 3D Shape Structure from a Single RGB Image

We propose to recover 3D shape structures from single RGB images, where ...
07/11/2012

Recovering Articulated Object Models from 3D Range Data

We address the problem of unsupervised learning of complex articulated o...
09/13/2018

Physical Primitive Decomposition

Objects are made of parts, each with distinct geometry, physics, functio...