Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids

04/22/2019
by   Despoina Paschalidou, et al.
8

Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.

READ FULL TEXT

page 1

page 6

page 7

page 12

page 14

page 15

page 16

page 17

research
02/15/2022

Compositional Scene Representation Learning via Reconstruction: A Survey

Visual scene representation learning is an important research problem in...
research
04/06/2020

DualSDF: Semantic Shape Manipulation using a Two-Level Representation

We are seeing a Cambrian explosion of 3D shape representations for use i...
research
03/07/2020

STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image

3D reconstruction from a single view image is a long-standing prob-lem i...
research
12/01/2016

Learning Shape Abstractions by Assembling Volumetric Primitives

We present a learning framework for abstracting complex shapes by learni...
research
11/15/2018

The Utility of Sparse Representations for Control in Reinforcement Learning

We investigate sparse representations for control in reinforcement learn...
research
01/06/2020

Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

The goal of many computer vision systems is to transform image pixels in...
research
01/18/2022

GANmouflage: 3D Object Nondetection with Texture Fields

We propose a method that learns to camouflage 3D objects within scenes. ...

Please sign up or login with your details

Forgot password? Click here to reset