College of Engineering, All Events

Back to Listing

Xiangru Huang "Representation learning for object detection from unlabeled LiDAR point cloud sequences"

Event Type
Seminar/Symposium
Sponsor
Computer Science, University of Illinois, CS 591 Vision Seminar
Virtual
wifi event
Date
Oct 4, 2022   1:00 pm  
Speaker
Xiangru Huang, Postdoc, MIT
Contact
Aditya Prakash
Views
53
Originating Calendar
Computer Science Speakers Calendar

Zoom: https://illinois.zoom.us/j/86238233298?pwd=Y29EWXRPOWtiZ09DczRYMXJZK3JRUT09

 

Title: Representation learning for object detection from unlabeled LiDAR point cloud sequences

 

Abstract: There are a huge number of LiDAR point cloud sequences that are generated everyday and a large fraction of them never get annotated. We will discuss how to use unlabeled LiDAR point cloud sequences in a way that requires no box annotations. The key observation is to look for "objects that are moving along smooth trajectories", or object traces.

Such intermediate data can be reliably extracted from LiDAR point cloud sequences without any learning techniques and is valuable by itself. For the downstream task, we design self-supervised pretext tasks that improve the performance of object detection.

 

Bio: Xiangru Huang received his PhD in Computer Science as a student of Qixing Huang from the University of Texas at Austin in 2020. His past research focused on efficient optimization algorithms, geometry processing and machine learning. In 2021, he then joined the Geometric Data Processing group as a postdoc, working with Prof. Justin Solomon. His more recent research focuses on self-supervised learning and point cloud sequences.

link for robots only