RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence | |
Hu, Ling2; Li, Qinsong3,4; Liu, Shengjun3; Yan, Dong-Ming1,5; Xu, Haojun3; Liu, Xinru3 | |
刊名 | GRAPHICAL MODELS |
2023-10-01 | |
卷号 | 129页码:11 |
关键词 | Shape correspondence Functional maps Unsupervised learning Optimal transport |
ISSN号 | 1524-0703 |
DOI | 10.1016/j.gmod.2023.101189 |
通讯作者 | Liu, Shengjun(shjliu.cg@csu.edu.cn) |
英文摘要 | In traditional deep functional maps for non-rigid shape correspondence, estimating a functional map including high-frequency information requires enough linearly independent features via the least square method, which is prone to be violated in practice, especially at an early stage of training, or costly post-processing, e.g. ZoomOut. In this paper, we propose a novel method called RFMNet (Robust Deep Functional Map Networks), which jointly considers training stability and more geometric shape features than previous works. We directly first produce a pointwise map by resorting to optimal transport and then convert it to an initial functional map. Such a mechanism mitigates the requirements for the descriptor and avoids the training instabilities resulting from the least square solver. Benefitting from the novel strategy, we successfully integrate a state-of -the-art geometric regularization for further optimizing the functional map, which substantially filters the initial functional map. We show our novel computing functional map module brings more stable training even under encoding the functional map with high-frequency information and faster convergence speed. Considering the pointwise and functional maps, an unsupervised loss is presented for penalizing the correspondence distortion of Delta functions between shapes. To catch discretization-resistant and orientation-aware shape features with our network, we utilize DiffusionNet as a feature extractor. Experimental results demonstrate our apparent superiority in correspondence quality and generalization across various shape discretizations and different datasets compared to the state-of-the-art learning methods. |
资助项目 | National Key Research and Development Program, China[2019YFB2204104] ; Hunan Provincial Natural Science Foundation of China[2021JJ30172] ; Hunan Provincial Natural Science Foundation of China[2023JJ40769] ; Natural Science Founda-tion of China[62172447] ; Natural Science Founda-tion of China[61876191] ; Natural Science Founda-tion of China[62172415] ; Open Project Program of the State Key Laboratory of Multimodal Artificial Intelligence Systems, China[202200025] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
WOS记录号 | WOS:001048855000001 |
资助机构 | National Key Research and Development Program, China ; Hunan Provincial Natural Science Foundation of China ; Natural Science Founda-tion of China ; Open Project Program of the State Key Laboratory of Multimodal Artificial Intelligence Systems, China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53999] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Liu, Shengjun |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Hunan First Normal Univ, Sch Math & Stat, Changsha, Peoples R China 3.Cent South Univ, Inst Engn Modeling & Sci Comp, Changsha, Peoples R China 4.Cent South Univ, Big Data Inst, Changsha, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Hu, Ling,Li, Qinsong,Liu, Shengjun,et al. RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence[J]. GRAPHICAL MODELS,2023,129:11. |
APA | Hu, Ling,Li, Qinsong,Liu, Shengjun,Yan, Dong-Ming,Xu, Haojun,&Liu, Xinru.(2023).RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence.GRAPHICAL MODELS,129,11. |
MLA | Hu, Ling,et al."RFMNet: Robust Deep Functional Maps for unsupervised non-rigid shape correspondence".GRAPHICAL MODELS 129(2023):11. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论