Episode Details
Back to Episodes
Stanford Seminar - Open-world Segmentation and Tracking in 3D
Description
October 11, 2024
Laura Leal-Taixé, NVIDIA
In this talk, I will discuss how to train models for detection and segmentation of 3D data, e.g., Lidar, without having to actually annotate data in the 3D domain. I will discuss different uses of pseudo-labels and present a demo for our Segment Anything in Lidar.
Uploaded 28-10-24
About the speaker: https://dvl.in.tum.de/team/lealtaixe/
More about the course can be found here: https://stanfordasl.github.io/robotics_seminar/
View the entire AA289 Stanford Robotics and Autonomous Systems Seminar playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rMeercb-kvGLUrOq4HR6BZD
► Check out the entire catalog of courses and programs available through Stanford Online: https://online.stanford.edu/explore
Learn more about your ad choices. Visit megaphone.fm/adchoices