3DV 2020 Tutorial on

3D Point Cloud Reconstruction and Segmentation

Anywhere on earth on November 28, 2020
Tutorial videos and slides will be released after the online events.


Speakers

Invited Panel Speakers


Overview

With the rapid development of cheaper and smaller depth cameras and lidar sensors, there is an increasing interest in scanning, processing and analysing real-world scenes in 3D. These scenes can range from highly-detailed objects to city-scale environments, and efficiently processing and analysing these scans lies at the epicentre of many computer vision applications, including autonomous driving, home robots and UAVs.

Point clouds are a convenient and efficient way to represent 3D data for most applications. However, to be able to use the point cloud data meaningfully, several necessary processing steps are needed to convert the raw scanner data to complete, semantically annotated scans which can be used for decision making and analysis. The two primary steps involved are:

In this tutorial, we aim to give an overview of why point clouds are an essential representation for 3D data, what applications point clouds can facilitate, and the techniques needed for point cloud reconstruction and segmentation.

We expect the tutorial to be suitable for an audience of varying knowledge of point clouds / 3D vision. For those who are going to work on an application related to point cloud or about to start research in this topic, this can be a systematic introduction that points you to various existing works. For those who have prior experience on point clouds, we are going to offer references to the most recent works to keep you up to date, and there are code snippets offered for specific algorithms, which might be of your interest.


Schedule


Time (GMT) Time (EST) Time (Beijing) Time (Tokyo) Topic
08:00-08:05 04:00-04:05 16:00-16:05 17:00-17:05 Welcome and Introduction
08:05-08:50 04:05-04:50 16:00-16:05 17:05-17:50 Background & Applications
Presenter: Dr. Yulan Guo
  • 3D data acquisition
  • 3D data representation
  • Point cloud learning
  • Applications
08:50-09:35 04:50-05:35 16:50-17:35 17:50-18:35 3D Point Cloud Reconstruction
Presenter: Dr. Ronald Clark
  • Dense point clouds as a map representation
  • Basics of SLAM and multi-view 3D reconstruction
  • State-of-the-art methods
  • Open challenges and new directions
09:35-10:20 05:35-06:20 17:35-18:20 18:35-19:20 3D Point Cloud Semantic Segmentation
Presenter: Mr. Qingyong Hu
  • Main challenges of 3D point cloud semantic segmentation
  • How to perform 3D point cloud semantic segmentation
  • Taxonomy: discretization, point and hybrid based algorithms
10:20-11:05 06:20-07:05 18:20-19:05 19:20-20:05 3D Point Cloud Instance Segmentation
Presenter: Dr. Bo Yang
  • Why and what is 3D point cloud instance segmentation
  • How to perform 3D point cloud instance segmentation
  • Taxonomy: proposal-based and proposal free algorithms
  • State-of-the-art algorithms
  • Performance evaluation
  • Summary and discussion
11:05-11:50 07:05-07:50 19:05-19:50 20:05-20:50 Panel Discussion
Host: Dr. Bo Yang & Qingyong Hu
  • Panelist introduction
  • Panelist presentations
  • Moderator-curated questions directed to the panelists
  • Questions from the audiences directed to the panelists
  • Virtue coffee break
11:50-12:00 07:50-08:00 19:50-20:00 20:50-21:00 Acknowledgments
*Please click here to know hours in your time-zone.

Please contact Qingyong Hu if you have question.