About The Forum
Calendar 2017 Poster Sessions : PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Student Name : Charles Qi
Advisor : Leonidas Guibas
Research Areas: Artificial Intelligence, Graphics/HCI
Advisor : Leonidas Guibas
Research Areas: Artificial Intelligence, Graphics/HCI
Abstract:
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
Bio:
Charles Ruizhongtai Qi is a fourth year Ph.D. student advised by Professor Leonidas J. Guibas at Stanford University. His research interest is on computer vision and machine learning. In particular, he works on 3D deep learning for semantic understanding and geometry inference. He has also worked on connecting 2D images and 3D shapes, to support knowledge transportation between these two modalities. He had publications in top tier conferences like CVPR, ICCV, NIPS and Siggraph Asia. Prior to joining Stanford, he got B.S. in Electronic Engineering from Tsinghua University in 2013. He was a research intern at Microsoft Research Asia in 2013 Spring and a software engineer intern at Google's self-driving car team in 2016 Summer.
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds and well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.
Bio:
Charles Ruizhongtai Qi is a fourth year Ph.D. student advised by Professor Leonidas J. Guibas at Stanford University. His research interest is on computer vision and machine learning. In particular, he works on 3D deep learning for semantic understanding and geometry inference. He has also worked on connecting 2D images and 3D shapes, to support knowledge transportation between these two modalities. He had publications in top tier conferences like CVPR, ICCV, NIPS and Siggraph Asia. Prior to joining Stanford, he got B.S. in Electronic Engineering from Tsinghua University in 2013. He was a research intern at Microsoft Research Asia in 2013 Spring and a software engineer intern at Google's self-driving car team in 2016 Summer.