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

by   Despoina Paschalidou, et al.

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to the simplicity of existing primitive representations, these methods fail to accurately reconstruct 3D shapes using a small number of primitives/parts. We address the trade-off between reconstruction quality and number of parts with Neural Parts, a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) which implements homeomorphic mappings between a sphere and the target object. The INN allows us to compute the inverse mapping of the homeomorphism, which in turn, enables the efficient computation of both the implicit surface function of a primitive and its mesh, without any additional post-processing. Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision. Evaluations on ShapeNet, D-FAUST and FreiHAND demonstrate that our primitives can capture complex geometries and thus simultaneously achieve geometrically accurate as well as interpretable reconstructions using an order of magnitude fewer primitives than state-of-the-art shape abstraction methods.


page 20

page 21

page 22

page 23

page 25

page 26

page 27

page 30


Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency

The task of shape abstraction with semantic part consistency is challeng...

Learning Shape Abstractions by Assembling Volumetric Primitives

We present a learning framework for abstracting complex shapes by learni...

DualSDF: Semantic Shape Manipulation using a Two-Level Representation

We are seeing a Cambrian explosion of 3D shape representations for use i...

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

Humans perceive the 3D world as a set of distinct objects that are chara...

Neural Star Domain as Primitive Representation

Reconstructing 3D objects from 2D images is a fundamental task in comput...

Primitive-based Shape Abstraction via Nonparametric Bayesian Inference

3D shape abstraction has drawn great interest over the years. Apart from...

Abstracting Sketches through Simple Primitives

Humans show high-level of abstraction capabilities in games that require...

Please sign up or login with your details

Forgot password? Click here to reset