3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks

08/04/2017
by   Chuhang Zou, et al.
0

The success of various applications including robotics, digital content creation, and visualization demand a structured and abstract representation of the 3D world from limited sensor data. Inspired by the nature of human perception of 3D shapes as a collection of simple parts, we explore such an abstract shape representation based on primitives. Given a single depth image of an object, we present 3D-PRNN, a generative recurrent neural network that synthesizes multiple plausible shapes composed of a set of primitives. Our generative model encodes symmetry characteristics of common man-made objects, preserves long-range structural coherence, and describes objects of varying complexity with a compact representation. We also propose a method based on Gaussian Fields to generate a large scale dataset of primitive-based shape representations to train our network. We evaluate our approach on a wide range of examples and show that it outperforms nearest-neighbor based shape retrieval methods and is on-par with voxel-based generative models while using a significantly reduced parameter space.

READ FULL TEXT

page 3

page 7

page 13

page 14

research
06/06/2018

Multi-chart Generative Surface Modeling

This paper introduces a 3D shape generative model based on deep neural n...
research
06/09/2019

Unsupervised Primitive Discovery for Improved 3D Generative Modeling

3D shape generation is a challenging problem due to the high-dimensional...
research
08/19/2021

3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces

3D Shape representation has substantial effects on 3D shape reconstructi...
research
08/05/2022

Learning to Generate 3D Shapes from a Single Example

Existing generative models for 3D shapes are typically trained on a larg...
research
12/01/2016

Learning Shape Abstractions by Assembling Volumetric Primitives

We present a learning framework for abstracting complex shapes by learni...
research
10/21/2020

Neural Star Domain as Primitive Representation

Reconstructing 3D objects from 2D images is a fundamental task in comput...
research
05/05/2021

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Humans perceive and construct the surrounding world as an arrangement of...

Please sign up or login with your details

Forgot password? Click here to reset