GRASS: Generative Recursive Autoencoders for Shape Structures

05/05/2017
by   Jun Li, et al.
0

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry.

READ FULL TEXT
research
09/14/2018

SCORES: Shape Composition with Recursive Substructure Priors

We introduce SCORES, a recursive neural network for shape composition. O...
research
08/12/2018

Structure-aware Generative Network for 3D-Shape Modeling

We present SAGNet, a structure-aware generative model for 3D shapes. Giv...
research
06/16/2019

Learning Part Generation and Assembly for Structure-aware Shape Synthesis

Learning deep generative models for 3D shape synthesis is largely limite...
research
10/02/2020

RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval

Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a ...
research
11/25/2019

StructEdit: Learning Structural Shape Variations

Learning to encode differences in the geometry and (topological) structu...
research
08/04/2018

Structure-Aware Shape Synthesis

We propose a new procedure to guide training of a data-driven shape gene...
research
09/01/2019

READ: Recursive Autoencoders for Document Layout Generation

Layout is a fundamental component of any graphic design. Creating large ...

Please sign up or login with your details

Forgot password? Click here to reset