ELLIS workshop on 3D Vision and Graphics 2025
Location: Lecture Hall, Ground Floor, Maria-von-Linden Strasse 6
20 March 2025 - 21 March 2025
For any questions, please contact Gerard Pons-Moll and Jessi Endress.
Learning for Graphics and Vision
The members of the ELLIS program ‘Learning for Graphics and Vision’ see a great opportunity to integrate classical computer graphics, geometry processing, and 3D vision principles more tightly within deep learning frameworks. The mission of this program is to connect researchers in machine learning, computer graphics, 3D computer vision, and geometry processing to discuss and explore how machine learning can benefit from graphics while opening new possibilities for graphics and vision.
Talks & Schedule
Thursday, 20 March 2025
| Time | Speaker | Talk Title |
|---|---|---|
| 15:00 | Gerard Pons-Moll | How much 3D do foundation models know? |
| 15:45 | Andreas Geiger | Learning to Splat |
| 16:30 | Coffee Break | |
| 16:45 | Andrea Tagliasacchi | Monte-carlo Neural Rendering |
| 17:30 | Vincent Lepetit | Automatic Annotations for 3D Scene Understanding |
| 18:15 | End |
Friday, 21 March 2025
| Time | Speaker | Talk Title |
|---|---|---|
| 09:00 | Federico Tombari | 3D Scene Understanding and Generation for Mixed Reality |
| 09:45 | Elliott Wu | From Pixels to 3D Motion: Modeling the Physical Natural World from Images |
| 10:30 | Coffee Break | |
| 10:45 | Gül Varol | 3D Human Motion & Language |
| 11:30 | Hendrik Lensch | 3D Relighting - Reconstruction and Generation |
| 12:15 | Lunch Break | |
| 13:00 | Niloy Mitra | Neural Geometry Processing |
| 13:45 | Victor Lempitsky | Capturing content for Virtual Reality: history and presence |
| 14:30 | Coffee Break | |
| 14:45 | Jan Eric Lenssen | Towards Generative Reasoning on Spatial Domains |
| 15:30 | End |
Invited Speakers
Event Photos
❮
❯
