Learning Shape Abstractions by Assembling Volumetric Primitives

12/01/2016
by   Shubham Tulsiani, et al.
0

We present a learning framework for abstracting complex shapes by learning to assemble objects using 3D volumetric primitives. In addition to generating simple and geometrically interpretable explanations of 3D objects, our framework also allows us to automatically discover and exploit consistent structure in the data. We demonstrate that using our method allows predicting shape representations which can be leveraged for obtaining a consistent parsing across the instances of a shape collection and constructing an interpretable shape similarity measure. We also examine applications for image-based prediction as well as shape manipulation.

READ FULL TEXT

page 1

page 6

page 7

page 13

research
03/18/2021

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

Impressive progress in 3D shape extraction led to representations that c...
research
04/16/2020

Combinatorial 3D Shape Generation via Sequential Assembly

3D shape generation has drawn attention in computer vision and machine l...
research
09/02/2023

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

The task of shape abstraction with semantic part consistency is challeng...
research
04/13/2016

VConv-DAE: Deep Volumetric Shape Learning Without Object Labels

With the advent of affordable depth sensors, 3D capture becomes more and...
research
04/22/2019

Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

Abstracting complex 3D shapes with parsimonious part-based representatio...
research
08/04/2017

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

The success of various applications including robotics, digital content ...
research
01/09/2019

Composite Shape Modeling via Latent Space Factorization

We present a novel neural network architecture, termed Decomposer-Compos...

Please sign up or login with your details

Forgot password? Click here to reset