Skip to main content

DiffusionPointLabel: Annotated Point Cloud Generation with Diffusion Model.

Li, T., Fu, Y., Han, X., Liang, H., Zhang, J. J. and Chang, J., 2022. DiffusionPointLabel: Annotated Point Cloud Generation with Diffusion Model. Computer Graphics Forum, 41 (7), 131-139.

Full text available as:

[img]
Preview
PDF
egPublStyle_PG2022_V20 depository.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

2MB

DOI: 10.1111/cgf.14663

Abstract

Point cloud generation aims to synthesize point clouds that do not exist in supervised dataset. Generating a point cloud with certain semantic labels remains an under-explored problem. This paper proposes a formulation called DiffusionPointLabel, which completes point-label pair generation based on a DDPM generative model (Denoising Diffusion Probabilistic Model). Specifically, we use a point cloud diffusion generative model and aggregate the intermediate features of the generator. On top of this, we propose Feature Interpreter that transforms intermediate features into semantic labels. Furthermore, we employ an uncertainty measure to filter unqualified point-label pairs for a better quality of generated point cloud dataset. Coupling these two designs enables us to automatically generate annotated point clouds, especially when supervised point-labels pairs are scarce. Our method extends the application of point cloud generation models and surpasses state-of-the-art models.

Item Type:Article
ISSN:0167-7055
Group:Faculty of Media & Communication
ID Code:40105
Deposited By: Symplectic RT2
Deposited On:09 Jul 2024 09:56
Last Modified:09 Jul 2024 09:56

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -