[]200倍的提速！华人博士生提出大场景三维点云语义分割新框架( 六 )

三维点云分割网络的scalability也是实际应用中一个比较重要的点。 i.e., 理想情况下train好的网络应该可以用于inference任意点数的输入点云，因为每个时刻采集到的点云的点数不一定是相同的。这也是RandLA-Net没有使用全局特征的原因， i.e. 确保学到的参数是agnostic to number of points.

顺便打一波广告，对于刚刚进入三维点云处理领域的同学，有一份最新的综述论文(Deep Learning for 3D Point Clouds: A Survey)可供参考，内含大量主流的点云目标分类，三维目标检测，三位场景分割算法的最新研究进展及总结。

牛津大学出品，作者团队介绍
论文合著者包括牛津大学博士生胡庆拥，杨波，谢林海，王智华；博士后Stefano Rosa；国防科技大学副教授郭玉兰；以及牛津大学教授Niki Trigoni和Andrew Markham 。

本文插图
胡庆拥

本文插图
杨波
其中论文一作胡庆拥研究方向是3D视觉和机器学习，专注于大规模3D点云分割和理解，动态点云处理和跟踪。论文二作(通讯作者)杨波专注于让智能机器从2D图片或3D点云中理解和重构完整3D场景。更多信息见个人主页:
https://qingyonghu.github.io
https://yang7879.github.io
Reference
[1] Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. PointNet: Deep learning on point sets for 3D classification and segmentation. CVPR, 2017.
[2] Charles R Qi, Li Yi, Hao Su, and Leonidas J Guibas. PointNet++: Deep hierarchical feature learning on point sets in a metric space. NeurIPS, 2017
[3] Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. PointCNN: Convolution on X-transformed points. NeurIPS, 2018.
[4] Wenxuan Wu, Zhongang Qi, and Li Fuxin. PointConv: Deep convolutional networks on 3D point clouds. CVPR, 2018.
[5] Fabian Groh, Patrick Wieschollek, and Hendrik P. A. Lensch.Flex-convolution (million-scale point-cloud learning beyond grid-worlds). ACCV, 2018
[6] Oren Dovrat, Itai Lang, and Shai Avidan. Learning to sample. CVPR, 2019.
[7] Itai Lang, Asaf Manor, and Shai Avidan. SampleNet: Differentiable Point Cloud Sampling. arXiv preprint arXiv:1912.03663 (2019).
[8] Abubakar Abid, Muhammad Fatih Balin, and James Zou. Concrete autoencoders for differentiable feature selection and reconstruction. ICML, 2019
[9] Jiancheng Yang, Qiang Zhang, Bingbing Ni, Linguo Li, Jinxian Liu, Mengdie Zhou, and Qi Tian. Modeling point clouds with self-attention and Gumbel subset sampling. CVPR, 2019.
[10] Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. Show, attend and tell: Neural image caption generation with visual attention. ICML, 2015
[11] Hugues Thomas, Charles R Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui, Franc ?ois Goulette, and Leonidas J Guibas. Kpconv: Flexible and deformable convolution for point clouds. ICCV, 2019.