Stefan Baumann

@StefanABaumann

PhD Student @ CompVis/Ommer Lab (@LMU_Muenchen, @ELLISforEurope) working on generative computer vision

Munich, Germany

stefan-baumann.eu

Joined September 2023

698 Following

851 Followers

Replies Reposts Media

Pinned
Stefan Baumann
@StefanABaumann
Jun 18
Now accepted to #ECCV2026 🎉
Stefan Baumann
@StefanABaumann
Jun 1
The internet is full of video. So why can't novel view synthesis just scale on it? Real-world video is simultaneously unposed, messy, and dynamic, breaking self-supervised NVS. We fixed that. RayDer learns static-scene NVS from dynamic internet video, scaling like an LLM. A🧵
00:00
4
Stefan Baumann
@StefanABaumann
Sep 11
Join us for our short oral today at 10:12 (in Palissad) at ECCV, and our poster (#442) in poster session 3 (morning session)
Stefan Baumann
@StefanABaumann
Jun 1
The internet is full of video. So why can't novel view synthesis just scale on it? Real-world video is simultaneously unposed, messy, and dynamic, breaking self-supervised NVS. We fixed that. RayDer learns static-scene NVS from dynamic internet video, scaling like an LLM. A🧵
00:00
Stefan Baumann
@StefanABaumann
Jun 5
You don't need a video model to predict motion. We'll talk about how to be 3000× faster at CVPR Poster 634, this morning at 10:45. Drop by and check it out!
Stefan Baumann
@StefanABaumann
Apr 13
You don't imagine the future by mentally rendering a movie. You trace how things move -- abstractly, sparsely, step by step. We built a model that does exactly this. It predicts motion, not pixels -- and it's 3,000× faster than video world models. Myriad, accepted at @CVPR 2026
1
Stefan Baumann
@StefanABaumann
Jun 1
The internet is full of video. So why can't novel view synthesis just scale on it? Real-world video is simultaneously unposed, messy, and dynamic, breaking self-supervised NVS. We fixed that. RayDer learns static-scene NVS from dynamic internet video, scaling like an LLM. A🧵
00:00
8
Stefan Baumann
@StefanABaumann
May 3
@eccvconf Thanks for the smooth review release! Could you please also make sure the rebuttal template is released properly? The overleaf link in the email is access-restricted, and the paper kits on the website don't include the rebuttal template
1