StarNet: Style-Aware 3D Point Cloud Generation

03/28/2023
by   Yunfan Zhang, et al.
0

This paper investigates an open research task of reconstructing and generating 3D point clouds. Most existing works of 3D generative models directly take the Gaussian prior as input for the decoder to generate 3D point clouds, which fail to learn disentangled latent codes, leading noisy interpolated results. Most of the GAN-based models fail to discriminate the local geometries, resulting in the point clouds generated not evenly distributed at the object surface, hence degrading the point cloud generation quality. Moreover, prevailing methods adopt computation-intensive frameworks, such as flow-based models and Markov chains, which take plenty of time and resources in the training phase. To resolve these limitations, this paper proposes a unified style-aware network architecture combining both point-wise distance loss and adversarial loss, StarNet which is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network that can effectively disentangle the Gaussian prior from input's high-level attributes in the mapped latent space to generate realistic interpolated objects. Experimental results demonstrate that our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks, but is more lightweight in model size, requires much fewer parameters and less time for model training.

READ FULL TEXT

page 1

page 6

page 7

page 8

06/28/2019

PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

As 3D point clouds become the representation of choice for multiple visi...
03/24/2022

WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation

We propose WarpingGAN, an effective and efficient 3D point cloud generat...
10/07/2021

Flow Plugin Network for conditional generation

Generative models have gained many researchers' attention in the last ye...
12/31/2019

Bas-relief Generation from Point Clouds Based on Normal Space Compression with Real-time Adjustment on CPU

Bas-relief generation based on 3d models is a hot topic in computer grap...
09/02/2022

Diffusion-based Molecule Generation with Informative Prior Bridges

AI-based molecule generation provides a promising approach to a large ar...
06/06/2021

Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction

Recently normalizing flows (NFs) have demonstrated state-of-the-art perf...
12/04/2020

ChartPointFlow for Topology-Aware 3D Point Cloud Generation

A point cloud serves as a representation of the surface of a three-dimen...

Please sign up or login with your details

Forgot password? Click here to reset