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

by   Despoina Paschalidou, et al.

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.


page 13

page 14

page 15

page 23

page 26


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

Impressive progress in 3D shape extraction led to representations that c...

Automatic pre-grasps generation for unknown 3D objects

In this paper, the problem of automating the pre-grasps generation for n...

Unsupervised Discovery of Parts, Structure, and Dynamics

Humans easily recognize object parts and their hierarchical structure by...

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

This paper presents a fully automatic framework for extracting editable ...

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

We propose to recover 3D shape structures from single RGB images, where ...

Recovering Articulated Object Models from 3D Range Data

We address the problem of unsupervised learning of complex articulated o...

Physical Primitive Decomposition

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