| Text-Free Controllable 3-D Point Cloud Generation | |
Xiao, Haihong1; Kang, Wenxiong1,2,3; Li YQ(李玉琼)4,5,6 ; Xu, Hongbin1
| |
| Corresponding Author | Kang, Wenxiong([email protected]) ; Li, Yuqiong([email protected]) |
| Source Publication | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
 |
| 2024 | |
| Volume | 73Pages:12 |
| ISSN | 0018-9456 |
| Abstract | Generating 3-D shapes with text inputs has long been a peculiar challenge in computer vision, which requires methodological know-how as well as a sense of art. Recently, text-to-image generation has driven remarkable progress, raising tremendous interest in text-guided shape generation, which further paves the way for industrial design. Nevertheless, prior efforts on text-guided 3-D synthesis either lack geometric details, are limited by the simple text input, or need expensive optimization and additional postprocessing, which make them unfriendly for novices. In this research, we present TFCNet, a novel approach for text-free controllable point cloud generation. In the training phase, we first design an empirically robust cross-modal skeletal point generator (CM-SPG) to predict skeletal points of the specific shape conditioned on the single image input. Then, we develop a diffusion-based dense point generator, which takes skeletal points as geometric guidance to produce dense point clouds that are faithful to the input images. In the inference phase, we propose an efficient text-free nonparametric transfer regime, which does not require separate training and can directly generate point cloud shapes while being semantically faithful to the provided text input. As evidenced by our experiments on the ShapeNet(v2) and CO3D datasets, our proposed method outperforms existing state of-the-art methods both quantitatively and qualitatively. |
| Keyword | 3-D point cloud text-free controllable point cloud generation text-guided 3-D generative modeling |
| DOI | 10.1109/TIM.2024.3353839 |
| Indexed By | SCI ; EI |
| Language | 英语 |
| WOS ID | WOS:001174112800006 |
| WOS Research Area | Engineering ; Instruments & Instrumentation |
| WOS Subject | Engineering, Electrical & Electronic ; Instruments & Instrumentation |
| Funding Project | National Natural Science Foundation of China |
| Funding Organization | National Natural Science Foundation of China |
| Classification | 一类 |
| Ranking | 1 |
| Contributor | Kang, Wenxiong ; Li, Yuqiong |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://dspace.imech.ac.cn/handle/311007/94751 |
| Collection | 流固耦合系统力学重点实验室 非线性力学国家重点实验室 |
| Affiliation | 1.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 511442, Peoples R China; 2.South China Univ Technol, Sch Future Technol, Guangzhou 510641, Peoples R China; 3.Pazhou Lab, Young Scholar Project Ctr, Guangzhou 510335, Peoples R China; 4.Chinese Acad Sci, Key Lab Mech Fluid Solid Coupling Syst, Inst Mech, Beijing 100190, Peoples R China; 5.Chinese Acad Sci, Inst Mech, State Key Lab Nonlinear Mech, Beijing 100190, Peoples R China; 6.Guangdong Aerosp Res Acad, Guangzhou 511458, Peoples R China |
| Recommended Citation GB/T 7714 | Xiao, Haihong,Kang, Wenxiong,Li YQ,et al. Text-Free Controllable 3-D Point Cloud Generation[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2024,73:12.Rp_Au:Kang, Wenxiong, Li, Yuqiong |
| APA | Xiao, Haihong,Kang, Wenxiong,李玉琼,&Xu, Hongbin.(2024).Text-Free Controllable 3-D Point Cloud Generation.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,73,12. |
| MLA | Xiao, Haihong,et al."Text-Free Controllable 3-D Point Cloud Generation".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 73(2024):12. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment