Projective Feature Learning for 3D Shapes with Multi-View Depth Maps
文献类型：期刊论文
| 作者 | Zhige Xie; Kai Xu; Wen Shan; Ligang Liu; Yueshan Xiong; Hui Huang |
| 刊名 | Computer Graphics Forum(Proceedings of Pacific Graphics 2015)
 |
| 出版日期 | 2015 |
| 英文摘要 | Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi-view depth image representation and propose a Multi-View Deep Extreme Learning Machine (MVD-ELM) to achieve fast and quality projective feature learning for 3D shapes. In contrast to existing multiview learning methods, our method ensures the feature maps learned for multiple views are mutually dependent via shared weights and, in each layer, their unprojections together form a valid 3D reconstruction of the input shape through using normalized convolution kernels. This leads to a more accurate 3D feature learning as shown by the encouraging results in several applications. Moreover, the 3D reconstruction property leads to clear visualization of the learned features, which further demonstrates the meaningfulness of our feature learning. |
| 收录类别 | SCI |
| 原文出处 | http://onlinelibrary.wiley.com/doi/10.1111/cgf.12740/full |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6835]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 作者单位 | Computer Graphics Forum(Proceedings of Pacific Graphics 2015) |
| 推荐引用方式 GB/T 7714 | Zhige Xie,Kai Xu,Wen Shan,et al. Projective Feature Learning for 3D Shapes with Multi-View Depth Maps[J]. Computer Graphics Forum(Proceedings of Pacific Graphics 2015),2015. |
| APA | Zhige Xie,Kai Xu,Wen Shan,Ligang Liu,Yueshan Xiong,&Hui Huang.(2015).Projective Feature Learning for 3D Shapes with Multi-View Depth Maps.Computer Graphics Forum(Proceedings of Pacific Graphics 2015). |
| MLA | Zhige Xie,et al."Projective Feature Learning for 3D Shapes with Multi-View Depth Maps".Computer Graphics Forum(Proceedings of Pacific Graphics 2015) (2015). |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。