「CV」 三维点云处理资源汇总
点云:point cloud,是三维点的集合,只需记录物体所在的点的坐标;没有规律性的排列,因此无法套用卷积神经网络;高分辨率下,比较节省内存与运算量,也比较适合表示高分辨率的三维物体;
点云处理概述
1 综述
-
3D Object Recognition with Ensemble Learning — A Study of Point Cloud-Based Deep Learning Models
2019-04-17 Paper
3D
·分类
·检测
·集成学习
·点云
-
Deep Learning for 3D Point Clouds: A Survey
2019-12-27 paper
2 理论
3 技术方向
3.1 GAN
- PU-Net: Point Cloud Upsampling Network
CVPR 2018 Paper | Tensorflow-Offical | Tensorflow-AE-GAN
点云上采样;
3.2 AE
附录
A 参考资料
- dragonlong. Trending in 3D Vision[EB/OL]. https://github.com/dragonlong/Trending-in-3D-Vision. -/2019-03-28.
- timzhang641. 3D-Machine-Learning[EB/OL]. https://github.com/timzhang642/3D-Machine-Learning. -/2019-03-28.
- poodar.chu. 点云感知 CVPR 2018 论文总结. https://zhuanlan.zhihu.com/p/41287237. 2018-08-04/2019-03-28
- QingyongHu. SoTA-Point-Cloud[EB/OL]. https://github.com/QingyongHu/SoTA-Point-Cloud. 2019/2020-01-22.
Comments