SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation

03/15/2022
by   Shidi Li, et al.
0

This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity. Our SPA-VAE infers a set of latent canonical candidate shapes for any given object, along with a set of rigid body transformations for each such candidate shape to one or more locations within the assembled object. In this way, noisy samples on the surface of, say, each leg of a table, are effectively combined to estimate a single leg prototype. When parts-based self-similarity exists in the raw data, sharing data among parts in this way confers numerous advantages: modeling accuracy, appropriately self-similar generative outputs, precise in-filling of occlusions, and model parsimony. SPA-VAE is trained end-to-end using a variational Bayesian approach which uses the Gumbel-softmax trick for the shared part assignments, along with various novel losses to provide appropriate inductive biases. Quantitative and qualitative analyses on ShapeNet demonstrate the advantage of SPA-VAE.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2021

EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation

This paper tackles the problem of parts-aware point cloud generation. Un...
research
05/16/2023

DualGenerator: Information Interaction-based Generative Network for Point Cloud Completion

Point cloud completion estimates complete shapes from incomplete point c...
research
01/25/2020

Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation

We present a novel approach to category-level 6D object pose and size es...
research
09/08/2020

Intraoperative Liver Surface Completion with Graph Convolutional VAE

In this work we propose a method based on geometric deep learning to pre...
research
06/10/2021

Spatially Invariant Unsupervised 3D Object Segmentation with Graph Neural Networks

In this paper, we tackle the problem of unsupervised 3D object segmentat...
research
03/26/2021

Which Parts determine the Impression of the Font?

Various fonts give different impressions, such as legible, rough, and co...

Please sign up or login with your details

Forgot password? Click here to reset