Alex Delitzas
@AlexDelitzas
Followers
69
Following
268
Media
0
Statuses
33
PhD student at ETH Zurich and Max Planck Institute for Informatics
Zurich, Switzerland
Joined August 2021
🚀 Join us on Thursday @CVPR to learn more about our work! "SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes" ✨️ Oral: Orals 4B on 3D vision (13:00-13:18) 👨🏫 Poster: Poster Session 4 (17:15-18:45) 🏠 Project page:
🚀Join us next week @CVPR, we present #SceneFun3D, the first large-scale dataset with realistic interaction labels in 3D scenes ✨Oral✨ 🏡Project page: https://t.co/URaRTqlMHx Labels include: 👉 Functional interactive elements 🗣️ Natural language task descriptions 🦾 3D motions
0
1
8
We are ready for the second day of #ICCV2025 🌺 you can find us at: 🐊 CroCoDL Workshop: 301B, 1:00PM ➡️ https://t.co/c1reN3cgJb ✨RANSAC Tutorial: 328, 1:00PM ➡️ https://t.co/ltPMZE9rqn
@zuriich92 @hermannsblum @majti89 @mapo1 @ICCVConference
0
8
14
#ICCV2025 is starting today 🌺 you can find us at: 🥽 LaMAria Tutorial: 325B, 1:00PM ➡️ https://t.co/X9UBfzNGm1 ☀️ OpenSUN3D Workshop: 306 B, 1:30PM ➡️ https://t.co/wmy9HtP7dw
@pesarlin @efedele16 @FrancisEngelman @AlexDelitzas @mapo1 @ICCVConference
0
8
14
1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.
12
48
335
Check our website for more details: https://t.co/QdPXeD0C4b And try our demo with your own images!
0
2
3
Can we learn to complete anything in Lidar without any manual supervision? Excited to share our #ICML2025 paper “Towards Learning to Complete Anything in Lidar” from my time at @nvidia with @CristianoSalto @NeeharPeri @meinhardt_tim @RdeLutio @AljosaOsep @lealtaixe! Thread🧵👇
1
12
60
Our workshop OpenSUN3D heads to @ICCVConference in Hawaii! 🌺 Working on open‑vocabulary 3D scene understanding? Our paper track is now open! Deadlines: ⏰Full papers (in proceedings): July 4 🗓️Extended abstracts and non-archival papers: Sept 1 🔗 https://t.co/lbzmGFx0Cf
0
10
43
The recordings from our workshop on Open-World 3D Scene Understanding @CVPR are now available! See you @ICCVConference in Honolulu🏄♂️ for the next edition! ➡️ https://t.co/bMc47CMdVR 🌍 https://t.co/4nSXaJHlfp
0
11
46
Interested in doing a PhD or PostDoc in 3D Vision in Switzerland 🇨🇭? This is an amazing opportunity! Francis is an excellent mentor with super cool ideas and always a pleasure to work with 🚀
Interested in 3D Vision, 3D Scene Understanding and 3D Generation? We have open PhD/PostDoc positions in Lugano, Switzerland - I'm at #CVPR2025, please reach out 🚀 or send me an email @CVPR
0
0
6
Are you at @CVPR? Check out our work on extending traditional 3D Scene Graphs to enable functional reasoning in 3D environments! Poster #343 (Highlight ✨️), today, Sat 14th at 5-7pm
Come check out our poster on Functional 3D Scene Graphs #343 @CVPR (Highlight) ✨ today, Sat 14th at 5-7pm ⏰ 🏡 https://t.co/Kl2SzCFRfc 📃 https://t.co/6l8PgBDyXR
0
0
4
Thanks @_akhaliq for sharing! During my internship at @NVIDIAAI, we explored zero-shot panoptic completion of Lidar scans — together with @CristianoSalto @NeeharPeri @meinhardt_tim @RdeLutio @lealtaixe @AljosaOsep!
2
12
72
✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superquadric primitives! Webpage: https://t.co/H1CmUxoB6E ArXiv: https://t.co/02bRm4EVYC
@BoyangSun @FrancisEngelman @mapo1 @cvg_ethz @ETH_AI_Center
3
37
181
I will be giving a talk on open-vocabulary 3D scene understanding at the next ZurichCV meetup! 🗓️ Date: Thursday, January 23rd 18:00 📍Location: @ETH_AI_Center, please see https://t.co/fCYT2YkTAq for additional details!
zurichai.ch
Ayca Takmaz on open-vocabulary 3D scene understanding.
0
9
45
Get ready for the next @CVPR workshop on OpenWorld 3D Scene Understanding ➡️ https://t.co/XqA2dyAp2Q We will be hosting: - prized challenge 🏆 (see https://t.co/URaRTqmkx5) - paper track 🗞️ - exciting keynote speakers 👩🏫 #CVPR2025
0
19
102
If you are at @eccvconf, check out the demo of OpenNerf and SceneFun3D at the Google Booth with @FrancisEngelman and @fedassa!
Stop by the #ECCV2024 Google Booth at 4:30pm CEST where Googlers Francis Engelmann and Federico Tombari will demo language-guided 3D search ( https://t.co/Mwg53JhPgL) and SceneFun3D, a new benchmark dataset for functional 3D scene understanding ( https://t.co/c2G4i5rdWT).
0
1
7
🚨Today @dvruette and I will present our work FABRIC at the FOCUS Workshop at #ECCV2024 🍝 Visit our poster to learn more about conditioning diffusion models with binary human feedback! 📍Room: Suite 2 🕰️Time: 16:30-17:30 (Monday) 🌍 Project: https://t.co/YramgR48UZ
0
4
16
Introducing our Keynote Speakers at this edition of the OpenSUN3D workshop #ECCV2024 (Sept 29, Sunday 14:00-15:30, Room: Amber 4) in Milano🇮🇹 Full schedule: https://t.co/XqA2dyAp2Q 🚀 @eccvconf @ETH_en @ETH_AI_Center @Stanford
0
8
32
Are you also a bit exhausted after #ICRA submission week? Let us brighten your day with a real "SpotLight" 💡 🔗 https://t.co/WKg2g7Hzaz 📄 https://t.co/YDcECCgySd We detect and generate interaction for almost any light switch and can then map which switch turns on which light.
1
2
10
It's a wrap! Thanks to all the fantastic speakers at the 2nd Open-Vocabulary 3D Scene Understanding workshop! @CVPR -- see you for the 3rd iteration @eccvconf in Milano, Italy 🇮🇹🍕🍝 ➡️ https://t.co/XqA2dyAp2Q
0
7
43
Come visit our Poster#342 in Session 4 @CVPR at 5pm this afternoon to learn more about how #SceneFun3D can help us understand functionalities and affordances in 3D environments 🤖
Today @AlexDelitzas✨presents #SceneFun3D the first large-scale 3D dataset with realistic interaction & functionality labels in 3D spaces🚀 🗣️Oral: 3D_Vision 1pm, Summit 🌆Poster: 342 5pm, Arch https://t.co/khcBJ1eCfm w/ @mapo1 @fedassa @aycatakmaz #CVPR24 @GoogleAI @ETH_en
0
0
4