PhD student at ETH Zurich and Max Planck Institute for Informatics
Zurich, Switzerland
Joined August 2021
- Tweets58
- Following193
- Followers109
- Likes417
Pinned Tweet
1/ Excited to present FunREC: "Reconstructing Functional 3D Scenes from Egocentric Interaction Videos" at #CVPR2026!
FunREC builds functional, interactable 3D digital replicas of real-world environments from a single egocentric interaction video.
👇 Here's me turning my own kitchen into a functional 3D digital twin, just by interacting with it.
🔗 Project page: functionalscenes.github.io
📄 Paper: arxiv.org/abs/2604.05621
🗓️ Poster: Session 4 (#654), Sat Jun 6, 16:45–18:45, ExHall A
Alex Delitzas retweeted
🚀 New from our team: CoMind (comind.ethz.ch/) - a dataset for AI that understands not just what I am doing, but what WE are doing together.
Two people. Two egocentric views. Gaze. Speech. 3D scenes. Social cues.
Accepted at #ECCV2026 🧵👇
Alex Delitzas retweeted
Kicking off @eccvconf tomorrow morning in
📍MalmöMässan (Room B) with:
🔹9:10: Matthias Niessner @MattNiessner (TUM/SpAItial)
🔹9:40: Dima Damen @dimadamen (Bristol/Google)
🔹11:00: Carl Doersch @CarlDoersch (Google)
🔹11:30: Peter Kontschieder (Meta)
➡️opensun3d.github.io
Alex Delitzas retweeted
📢 Looking for #PhD? Ψάχνεις για #διδακτορικό? My team #3DI has 3 open positions in our #ERC project on perceiving 3D human-object interaction; a step towards world models for avatars/physical-AI!
👉Apply: dtzionas.com/apply/ →Early 🐦 eats 🪱
📍@Auth_University Thessaloniki/Greece
🙏Plz help spread the word
Alex Delitzas retweeted
How well do vision foundation models understand the parts and the structure of objects?
Introducing SOCO, our benchmark for Semantic Object Correspondence, appearing as a Spotlight at #ECCV2026.
🌐 genintel.github.io/SOCO/
👇
Alex Delitzas retweeted
Does 3D reconstruction have to be complex?
We answer this question with PointDiT (#ICML2026): a minimalist pixel-space Diffusion Transformer without bells and whistles.
We show that a plain ViT can estimate dense 3D point maps by operating directly on raw patches. No hybrid ViT+Conv architectures, no lossy VAEs, no complicated training losses. (1/5) 🧵👇
Alex Delitzas retweeted
How can 4D reconstruction leverage generative priors for unseen dynamics and regions, while respecting the constraints of projective geometry?
Introducing World from Motion: a generative method that reconstructs freely-renderable dynamic 3D Gaussians from monocular video. 🧵🔥
Alex Delitzas retweeted
Happy to share that I’ll be joining Ulm University this fall! We have open PhD positions in egocentric vision and embodied AI, with opportunities for co-supervision by Dima Damen @dimadamen and close collaboration with the Aria team. More details below 👇
5/ To motivate research on functional 3D scene understanding, we also introduce two new 4D datasets:
RealFun4D — 351 in-the-wild human-scene interactions in 60 real-world indoor spaces
OmniFun4D — 127 photorealistic simulated interactions in 12 synthetic indoor spaces
Both come richly annotated: RGB-D video, camera poses, hand & interacted part masks, 6D part poses, articulation parameters, interaction intervals, action text descriptions, and full 3D reconstructions of the static scene + every moving part.
7/ Joint work with Alexey Gavryushin, @cyrus_zhang1, Tommaso Di Mario, Boyang Sun, Rishabh Dabral, Leonidas Guibas, Christian Theobalt, @mapo1, @FrancisEngelman & @majti89 🙌
@cvg_ethz · @VcaiMpi · @Stanford · Microsoft Spatial AI Lab · Thinking Shapes Lab @USI_university
Alex Delitzas retweeted
Happening now, @AlexDelitzas presenting FunREC "Reconstructing Functional 3D Scenes from Egocentric Interaction Videos "@CVPR - come check our Poster on Sat. June 6 4:45PM-6:45PM
Alex Delitzas retweeted
Join us at @ETH_en for an afternoon on embodied AI with @JitendraMalikCV, Vladlen Koltun, @ylecun, and
@SongShuran.
📍 Location: ETH Zurich, ML Building, Room D28
🗓 Date: Friday, 29 May
⏰ Time: 14:00 – 18:30
✅ Register here: luma.com/mv3z9bc9
Alex Delitzas retweeted
Had a fantastic time at @zurichnlp🇨🇭amazing audience and discussions!
Showed how superquadrics can represent the world, with:
- SuperDec super-dec.github.io
- SuperFlex superflex3d.github.io
- SpaceControl spacecontrol3d.github.io
Thanks for the kind invite @aycatakmaz🙏
Alex Delitzas retweeted
What happens when you combine Meta's Project Aria with custom force-sensing grippers? 🤖👓
The new Hoi! dataset uses the egocentric perspective from Aria glasses to bridge the gap between what is seen, done, and felt; coupling egocentric vision and eye-tracking with real-world force sensing.
Great work from our partners at the @ETH_en Computer Vision and Geometry group! We’re looking forward to the presentations and discussions at #CVPR2026. 🥳
📰 Paper: lnkd.in/eXASwxPy
🏠 Webpage: lnkd.in/ePXpWZmW
📢 @mapo1, @zuriich92 , @hermannsblum
Alex Delitzas retweeted
Just as we say goodbye to Vancouver (YVR)🇨🇦🥹, it’s time to reveal our next destination! ✈️
From the Pacific coast to the Mediterranean sea...
We are thrilled to announce that #3DV2027 is heading to Thessaloniki, Greece (SKG)! 🇬🇷🥳
See you there in Mid-April 2027! 🌍
🤖 Made with AI
Alex Delitzas retweeted
AnyUp has been accepted to ICLR 2026 as an oral presentation! ⭐️
I'm looking forward to presenting it in Rio. If you're interested, please come by my talk or poster. 🇧🇷
