Elisabetta Fedele

✨We introduce SuperDec, a new method which allows to create compact 3D scene representations via decomposition into superquadric primitives! Webpage: super-dec.github.io ArXiv: arxiv.org/abs/2504.00992 @BoyangSun @FrancisEngelman @mapo1 @cvg_ethz @ETH_AI_Center

Multi-modal 3D asset generation: Text conditioned ✅ Image conditioned ✅ … and now: Spatial conditioned 🚀✨

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🧵👇

Feynman on beauty of the flower: I have a friend who’s an artist and has sometimes taken a view which I don’t agree with very well. He’ll hold up a flower and say “look how beautiful it is,” and I’ll agree. Then he says “I as an artist can see how beautiful this is but you as a…

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 🔗 opensun3d.github.io

The recordings from our workshop on Open-World 3D Scene Understanding @CVPR are now available! See you @ICCVConference in Honolulu🏄‍♂️ for the next edition! ➡️ youtube.com/playlist?list=… 🌍 opensun3d.github.io

I’ll be presenting at poster #80 tomorrow at 10:30 — come say hi!

Come check out our poster on Functional 3D Scene Graphs #343 @CVPR (Highlight) ✨ today, Sat 14th at 5-7pm ⏰ 🏡 openfungraph.github.io 📃 arxiv.org/abs/2503.19199

If you are looking for a PhD or a PostDoc in 3D computer vision you shouldn’t miss this opportunity! Francis is an amazing mentor and always has super cool ideas✨🚀 #CVPR25

And finally Jaime Corsetti presenting “Functionality understanding and segmentation in 3D scenes”, one of the winners of our SceneFun3D challenge 🏆✨ ⏰: 5:15-5:45 pm 📍: Room 105A 🌍: opensun3d.github.io @CVPR #OpenSUN3D

Björn Ommer presenting now “Efficient Repurposing of T2I Representations Across Modalities: 2D, 3D, and Beyond”! ⏰: 4:45-5:15 pm 📍: Room 105A 🌍: opensun3d.github.io @CVPR #OpenSUN3D

Lukas Schmid presenting now “Hierarchical Methods for Task-driven and Dynamic Scene Understanding”! ⏰: 4:15-4:45 pm 📍: Room 105A 🌍: opensun3d.github.io @CVPR #OpenSUN3D

Afshin Dehghan presenting now “3D Scene Intelligence: Points, Transformers & Multimodal LLMs”! ⏰: 3:45-4:15 pm 📍: Room 105A 🌍: opensun3d.github.io @CVPR #OpenSUN3D

Time for the poster session in Hall D (posters 452-466) ☕️ see you again in Room 105A at 3:45 pm ✨ 📍: Room 105 A 🌍: opensun3d.github.io @CVPR #OpenSUN3D

Laura Leal-Taixé presenting now “Towards a Foundation Model for 4D (LiDAR)”! ⏰: 2:30-3:00 pm 📍: Room 105A 🌍: opensun3d.github.io @lealtaixe @CVPR #OpenSUN3D

Jeannette Bohg presenting now “The Challenges and Opportunities of Mobile Manipulation”! ⏰: 2:00-2:30 pm 📍: Room 105A 🌍: opensun3d.github.io @leto__jean @CVPR

OpenSUN3D workshop starting now in Room 105A @CVPR 🚀 📍: Room 105A 🕰️: 2:00-6:00 pm 🌍: opensun3d.github.io

Join us at OpenSUN3D☀️ workshop this afternoon @CVPR 🚀 📍: Room 105 A 🕰️: 2:00-6:00 pm 🌍: opensun3d.github.io @afshin_dn @leto__jean @lealtaixe

If you are interested in Open-World 3D Scene Understanding you shouldn’t miss our workshop OpenSUN3D! We will be @CVPR with an amazing line-up of speakers ✨🚀 #OpenSUN3D #CVPR2025