in ,

(video) 3D Deep Learning & Self Supervision, Prof. Matthias Nießner

2nd 3D-DLAD Workshop at IV 2020 Las Vegas

Speaker : Prof. Matthias Nießner
Abstract : In this talk, I talk about how we can use 3D data to self-supervise existing problems, and how in particular panoramic images such as from the Matterport3D dataset can fuel many computer vision tasks. I will further talk about how to leverage these ideas in the context of 3D shape reconstruction / completion, getting high-quality 3D models even when no ground truth data is available in real-world scan.

What do you think?

484 points
Upvote Downvote

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

(video) Voyage’s Self-Driving A.I. in Action

(video) RoboSense MEMS LiDAR “M1” Shows Excellent Perception Details on Chinese City Intersection