SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

	SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
	Yifan Xu; Tianqi Fan; Mingye Xu; Long Zeng; Yu Qiao
	2018
会议日期	2018
英文摘要	Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed Spi- derCNN, to efficiently extract geometric features from point clouds. Spi- derCNN is comprised of units called SpiderConv, which extend convolu- tional operations from regular grids to irregular point sets that can be embedded in Rn, by parametrizing a family of convolutional filters. We design the filter as a product of a simple step function that captures local geodesic information and a Taylor polynomial that ensures the expres- siveness. SpiderCNN inherits the multi-scale hierarchical architecture from classical CNNs, which allows it to extract semantic deep features. Experiments onModelNet40 demonstrate that SpiderCNN achieves state- of-the-art accuracy 92.4% on standard benchmarks, and shows compet- itive performance on segmentation task.
URL标识	查看原文
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/13689]
专题	深圳先进技术研究院_集成所
推荐引用方式 GB/T 7714	Yifan Xu,Tianqi Fan,Mingye Xu,et al. SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters[C]. 见:. 2018.