Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds

06/07/2021
by   Kaizhi Yang, et al.
0

Representing complex 3D objects as simple geometric primitives, known as shape abstraction, is important for geometric modeling, structural analysis, and shape synthesis. In this paper, we propose an unsupervised shape abstraction method to map a point cloud into a compact cuboid representation. We jointly predict cuboid allocation as part segmentation and cuboid shapes and enforce the consistency between the segmentation and shape abstraction for self-learning. For the cuboid abstraction task, we transform the input point cloud into a set of parametric cuboids using a variational auto-encoder network. The segmentation network allocates each point into a cuboid considering the point-cuboid affinity. Without manual annotations of parts in point clouds, we design four novel losses to jointly supervise the two branches in terms of geometric similarity and cuboid compactness. We evaluate our method on multiple shape collections and demonstrate its superiority over existing shape abstraction methods. Moreover, based on our network architecture and learned representations, our approach supports various applications including structured shape generation, shape interpolation, and structural shape clustering.

READ FULL TEXT

page 1

page 6

page 7

page 9

page 10

research
10/25/2018

Practical Shape Analysis and Segmentation Methods for Point Cloud Models

Current point cloud processing algorithms do not have the capability to ...
research
09/03/2021

Representing Shape Collections with Alignment-Aware Linear Models

In this paper, we revisit the classical representation of 3D point cloud...
research
01/04/2021

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

Although unsupervised feature learning has demonstrated its advantages t...
research
07/15/2020

Learning Part Boundaries from 3D Point Clouds

We present a method that detects boundaries of parts in 3D shapes repres...
research
01/13/2022

Learning Semantic Abstraction of Shape via 3D Region of Interest

In this paper, we focus on the two tasks of 3D shape abstraction and sem...
research
12/27/2021

SurFit: Learning to Fit Surfaces Improves Few Shot Learning on Point Clouds

We present SurFit, a simple approach for label efficient learning of 3D ...
research
03/10/2019

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

For the task of mobility analysis of 3D shapes, we propose joint analysi...

Please sign up or login with your details

Forgot password? Click here to reset