Login
Materials for Foundational Models in 2D and 3D Computer Vision
Template for report: Link
Zoom link for online attendees:
Topic: Seminar FMCV Time: Mar 17, 2025 09:00 AM Amsterdam, Berlin, Rome, Stockholm, Vienna Join Zoom Meeting https://tum-conf.zoom-x.de/j/68147361037?pwd=IgFH452t1qAkZU3Yev6ZBba8S6fuOI.1
Meeting ID: 681 4736 1037 Passcode: 058734
Topic Assignment
| Name | Topic | Contact | Presentation Time |
|---|---|---|---|
| Elena Alegret Regalado | Masked autoencoders are scalable vision learners | Tarun | 09:00 - 09:45 |
| Jan-Michael van der Linde | Learning transferable visual models from natural language supervision | Tarun | 09:45 - 10:30 |
| Guillermo Figueroa | Florence: A new foundation model for computer vision | Tarun | 10:45 - 11:30 |
| Vayun Goel | Segment anything | Dominik | 11:30 - 12:15 |
| Selen Çiğdem | SAM 2: Segment Anything in Images and Videos | Dominik | 12:15 - 13:00 |
| Viktor Svensson | Zero-shot text-to-image generation | Dominik | 14:00 - 14:45 |
| Tümay Tayyar Kamburoğlu | High-resolution image synthesis with latent diffusion models | Dominik | 14:45 - 15:30 |
| Yeeun Song | DreamFusion: Text-to-3D using 2D Diffusion | Tarun | 15:45 - 16:30 |
| Jun Wang | ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation | Tarun | 16:30 - 17:15 |
