Open sebastianahnert opened 3 years ago
This is an interesting thought!
Alan and I were talking about a related challenge, namely relating 2D shape descriptors to 3D ones.
One option could be 3D Polyominoes.
There’s also the question whether we’d want to look at 2D projections or cross-sections.
On 5 Aug 2021, at 17:20, Scott Hosking @.***> wrote:
Can we build up a synthetic dataset of 3D objects projected onto 2D images?
thoughts @sebastianahnert https://github.com/sebastianahnert ?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/alan-turing-institute/scivision/issues/41#issuecomment-893590006, or unsubscribe https://github.com/notifications/unsubscribe-auth/AKSQAIXPYTXPCHJIGDMDLQDT3K25XANCNFSM5BUEHCUA. Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&utm_campaign=notification-email.
Dr Sebastian E. Ahnert
University Lecturer Department of Chemical Engineering & Biotechnology University of Cambridge
Senior Research Fellow The Alan Turing Institute
Can we build up a synthetic dataset of 3D objects projected onto 2D images?
thoughts @sebastianahnert ?