George Paschalidis

PhD Student at @UvA_Amsterdam | 4D Human Perception

[Despoina Paschalidou @paschalidoud_1]

It’s been a while since I posted here, but I’m very excited to share what our team at @nvidia has been building over the past year!

After a year of active development, we’re getting ready to release SIL-Wheel to the world: a one-stop shop platform for data-centric workflows in large-scale video model training.

Built by researchers, for researchers, SIL-Wheel brings together search, curation, annotation, evaluation, and analysis for large video datasets in one centralized framework.

Want a sneak peek before the official release? Come by the NeXD26 Workshop @CVPR tomorrow at 10:30!🚀

[International Conference on 3D Vision (3DV) @3DVconf]

Looking for a nice home for your paper? #3DV2027 is waiting! 🎉

⏰ Conference dates: April 6-9, 2027
✈️ Place: #Thessaloniki (#SKG), #Greece 🇬🇷

📝 Paper ddl: Aug 28
🎥 Supp ddl: Sep 02
🆕 Rebuttal only upon invite for borderline papers!

#CallForPapers: https://t.co/6Fy3QG7PRE

[George Paschalidis @gkpaschalidis]

Recovering 3D object pose and shape from a single image is really challenging. SDFit introduces a novel framework that deals successfully with this problem. Congrats to @anticdimi for the amazing work!!!

[Dimitrije Antić @anticdimi]

Intelligent systems need to understand #3D Objects from single images. However, recent SotA methods work well for unoccluded views & common poses, and prioritize shape over pose. We tackle this by developing #SDFit #ICCV2025 a novel Render-n-Compare framework for 3D objects that:
👉 Is robust to occlusion & uncommon poses
👉 Treats both Shape & Pose as 1st class citizens

(1/6🧵)

[Sai Kumar Dwivedi @saidwivedi]

🔥 New InteractVLM Models Released! (#CVPR2025)

🔹 Single Model for Joint Human-Object Contact
🔹 3D Human Contact trained on more data, now supports foot-ground contact
🔹 Direct Contact Estimation on Images (2D)

🔗 [Code] https://t.co/pHmxvl6JUn

[Dimitris Tzionas @dimtzionas]

🎯 Modeling how people interact with objects in #3D is important for both 3D #perception from 2D images, and for 3D #avatar synthesis for AR/VR
👉 I gave a talk on this @ #BMVA 'Symposium on Digital Humans'
👉 Video: https://t.co/RJs3fOygDX
👉 Slides: https://t.co/8wJwEGYuss

[Dimitris Tzionas @dimtzionas]

🤔 Can we synthesize videos of realistic physical interactions?
🎉 Our InterDyn #CVPR2015 method controls a video foundational model via a 2D signal of an actor's motion!
👉 Project: https://t.co/2yauHvFsz6
👉 The 1st authors are in the job market!
@HavenFeng,@rick_akker25502

[George Paschalidis @gkpaschalidis]

If you are interested in 3D Whole-Body Grasp synthesis you should definitely check our recent work CWGrasp!!!

[Dimitris Tzionas @dimtzionas]

📢 We present CWGrasp, a framework for generating 3D Whole-body Grasps with Directional Controllability 🎉
Specifically:
👉 given a grasping object (shown in red color) placed on a receptacle (brown color)
👉 we aim to generate a body (gray color) that grasps the object.

🧵 1/10

[Dimitris Tzionas @dimtzionas]

CWGrasp will be presented @3DVconf #3DV2025

Authors: @gkpaschalidis (1st), @romananana__, @anticdimi, @omidtaherii
Collab: @UvA_Amsterdam @UvA_Science, @PerceivingSys @MPI_IS

Project: https://t.co/CBGVEmLrNA
Paper: https://t.co/VuJbKhsVmk
Code: https://t.co/eubGEbezFL

🧵 10/10