11-29, 16:40–16:50 (Asia/Seoul), Seoul Archive
In the majority of cases, I find that deep learning of point cloud data, e.g., in the case of classification, learning with datasets available on the Internet is not accurate enough when trying to solve our specific practical problems. We are then forced to manually label the point cloud, which can be time consuming and difficult to achieve accuracy in detail when processing on a 2D display, as point cloud data is generally not highly visible.
Therefore, I am trying to speed up the labeling of point clouds using VR. I would like to share my idea with you this time.
Age : 25
I do VR Point Cloud Processing as a freelancer.
I am also working at National Institute of Advanced Industrial Science and Technology, AI research Center.
My portforio:
https://nakamurata.notion.site/Taisei-Nakamura-6ad6e7c34d7f49a4828af406be0b03ea?pvs=4