StructureNet: Hierarchical Graph Networks for 3D Shape Generation

by   Kaichun Mo, et al.

The ability to generate novel, diverse, and realistic 3D shapes along with associated part semantics and structure is central to many applications requiring high-quality 3D assets or large volumes of realistic training data. A key challenge towards this goal is how to accommodate diverse shape variations, including both continuous deformations of parts as well as structural or discrete alterations which add to, remove from, or modify the shape constituents and compositional structure. Such object structure can typically be organized into a hierarchy of constituent object parts and relationships, represented as a hierarchy of n-ary graphs. We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries. Technically, we accomplish this by drawing inspiration from recent advances in graph neural networks to propose an order-invariant encoding of n-ary graphs, considering jointly both part geometry and inter-part relations during network training. We extensively evaluate the quality of the learned latent spaces for various shape families and show significant advantages over baseline and competing methods. The learned latent spaces enable several structure-aware geometry processing applications, including shape generation and interpolation, shape editing, or shape structure discovery directly from un-annotated images, point clouds, or partial scans.


page 12

page 14

page 15

page 24

page 26

page 27

page 28

page 29


DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry

3D shape generation is a fundamental operation in computer graphics. Whi...

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

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

Learning Part Generation and Assembly for Structure-aware Shape Synthesis

Learning deep generative models for 3D shape synthesis is largely limite...

GRASS: Generative Recursive Autoencoders for Shape Structures

We introduce a novel neural network architecture for encoding and synthe...

Parsing Geometry Using Structure-Aware Shape Templates

Real-life man-made objects often exhibit strong and easily-identifiable ...

Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces

Modeling relations between components of 3D objects is essential for man...

A Non-structural Representation Scheme for Articulated Shapes

For representing articulated shapes, as an alternative to the structured...

Code Repositories


StructureNet: Hierarchical Graph Networks for 3D Shape Generation

view repo


Physically-feasible StructureNet. This is a fork of the original work by, which has been extended as shown in the paper "Extending StructureNet to Generate Physically Feasible 3D Shapes", published at the GRAPP conference in 2021.

view repo