InterTrack will appear at International Conference on 3D Vision 25. Data and code available, check it out! I hope to see you in Singapore!

If you are interested in Human pose learned at scale, neural fields of neural network weights... or breakdance, talk to István Sárándi at NeurIPS Conference

I will talk today at 17 at the AI doctoral academy, if you are interested feel free to join remotely: i-aida.org/events/how-to-…

If you want to know which foundation models are best for 3D, check out Yue Chen feat2gs. Key idea is to predict Gaussian Splats from foundation features and use novel view synthesis as the metric for 3D accuracy.

I will teach a course on modern 3D computer vision, starting with classical stuff (epipolar geo, camera, stereo) and progress to neural rendering and transformer based reconstruction methods like dust3r. Can someone point me to good slide sources?

If you are at ICRA and are interested in 3d pose estimation, don't miss this talk

Happy to be in Nashville to catch up with friends and colleagues! Can someone point me to a place where they sell European plug adapters? ... around the convention center.

I'll talk about human-object/scene interactions, capture and synthesis: Today at 11.30 📍 Room 101 D, Music City Center 🔗 humanoid-agents.github.io Workshop will be stream vía zoom on cvpr official link.

I'll give 2 talks today: 9.25 am: 3d humans in the 3d world poets2024.github.io/poets2025/ 3pm: how to learn 3d human foundation models sites.google.com/view/3d-humans… Looking forward to the workshops!

Nice demo from Unitree. I shaked hands with it but didn't dare to box against it :-)

Had a blast at cvpr! Unfortunately, I have to return earlier! Really nice to see many researchers excited to share their cool works and ideas. The best part: catching up with old friends and colleagues!

Real time online 3D reconstruction of 3D scene and humans represented with SMPL. fanegg.github.io/Human3R/ I don't get tired of looking at these results

Can we tell the human pose from an object alone? And the object given the human? With TriDi we can sample from any conditionl distribution of human, object and interaction. With the same model! Stop by our poster if you are at ICCV25! github.com/ptrvilya/tridi

Can we tell the human pose from an object alone? And the object given the human? With TriDi we can sample from any conditionl distribution of human, object and interaction. With the same model! Stop by our poster if you are at ICCV25! github.com/ptrvilya/tridi