CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 三维可视计算
Diff-pcg: diffusion point cloud generation conditioned on continuous normalizing flow
Yu T(余挺); Meng WL(孟维亮); Wu ZQ(吴仲琦); Guo JW(郭建伟); Zhang XP(张晓鹏)
Source PublicationThe Visual Computer
ISSN0178-2789
2024
Pages1-15
Corresponding AuthorGuo, Jianwei(jianwei.guo@nlpr.ia.ac.cn) ; Zhang, Xiaopeng(xiaopeng.zhang@ia.ac.cn)
Abstract

With the continuous advancement of computer technology and graphic capabilities, the creation of 3D point clouds holds great promise across various fields. However, previous methods in this area are still facing huge challenges, such as complex training setups and limited precision in generating high-quality 3D content. Taking inspiration from the denoising diffusion probabilistic model, we propose Diff-PCG, a Diffusion Point Cloud Generation Conditioned on Continuous Normalizing Flow for 3D generation. Our approach seamlessly combines forward diffusion and reverse processes to produce high-quality 3D point clouds. Moreover, we include a trainable continuous normalizing flow that controls the foundational structure of the point cloud to enhance the representation ability of the encoded information. Extensive experiments validate the efficacy of our approach in generating high-quality 3D point clouds.

Keyword3D shape generation Diffusion model Continuous normalizing flow Point cloud
DOI10.1007/s00371-024-03370-x
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China ; Guangdong Science and Technology Program[2023B1515120026] ; Beijing Natural Science Foundation[L231013] ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University[VRLAB2023B01] ; [U22B2034] ; [U21A20515] ; [62376271] ; [62172416] ; [62262043] ; [62102414] ; [62365014] ; [62162044]
Funding OrganizationNational Natural Science Foundation of China ; Guangdong Science and Technology Program ; Beijing Natural Science Foundation ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University
WOS Research AreaComputer Science
WOS SubjectComputer Science, Software Engineering
WOS IDWOS:001198420700002
PublisherSPRINGER
Sub direction classification计算机图形学与虚拟现实
planning direction of the national heavy laboratory环境多维感知
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57342
Collection多模态人工智能系统全国重点实验室_三维可视计算
Corresponding AuthorGuo JW(郭建伟); Zhang XP(张晓鹏)
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.Institute of Science and Development, Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Yu T,Meng WL,Wu ZQ,et al. Diff-pcg: diffusion point cloud generation conditioned on continuous normalizing flow[J]. The Visual Computer,2024:1-15.
APA Yu T,Meng WL,Wu ZQ,Guo JW,&Zhang XP.(2024).Diff-pcg: diffusion point cloud generation conditioned on continuous normalizing flow.The Visual Computer,1-15.
MLA Yu T,et al."Diff-pcg: diffusion point cloud generation conditioned on continuous normalizing flow".The Visual Computer (2024):1-15.
Files in This Item: Download All
File Name/Size DocType Version Access License
s00371-024-03370-x.p(2471KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yu T(余挺)]'s Articles
[Meng WL(孟维亮)]'s Articles
[Wu ZQ(吴仲琦)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yu T(余挺)]'s Articles
[Meng WL(孟维亮)]'s Articles
[Wu ZQ(吴仲琦)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yu T(余挺)]'s Articles
[Meng WL(孟维亮)]'s Articles
[Wu ZQ(吴仲琦)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: s00371-024-03370-x.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.