The N-Body Problem: Parallel Execution from Single-Person Egocentric Video
Input: Single-person egocentric video 👤
Out: imagine how these tasks can be performed faster by N > 1 people, correctly e.g. N=2 👥
📎 arxiv.org/abs/2512.11393
👀 zhifanzhu.github.io/ego-nbody/
1/4
The N-Body Problem: Parallel Execution from Single-Person Egocentric Video
Input: Single-person egocentric video 👤
Out: imagine how these tasks can be performed faster by N > 1 people, correctly e.g. N=2 👥
📎 arxiv.org/abs/2512.11393
👀 zhifanzhu.github.io/ego-nbody/
1/4
This isn't one animal. It's actually a colony of individual animals called zooids. Each has a specialized role. From the orb-like swimming nectophores to the bright orange stinging tentacles, they're essential to the survival of all.
This isn't one animal. It's actually a colony of individual animals called zooids. Each has a specialized role. From the orb-like swimming nectophores to the bright orange stinging tentacles, they're essential to the survival of all.
Apply to the PhD in Engineering program by December 2nd ⌛: www.postgraduate.study.cam.ac.uk/courses/dire...
Apply to the PhD in Engineering program by December 2nd ⌛: www.postgraduate.study.cam.ac.uk/courses/dire...
Yu Hu, Chong Cheng, Sicheng Yu ... Hao Wang
arxiv.org/abs/2511.19971
Trending on www.scholar-inbox.com
Yu Hu, Chong Cheng, Sicheng Yu ... Hao Wang
arxiv.org/abs/2511.19971
Trending on www.scholar-inbox.com
David Nordström, Johan Edstedt, Fredrik Kahl, Georg Bökman
arxiv.org/abs/2511.17309
Trending on www.scholar-inbox.com
David Nordström, Johan Edstedt, Fredrik Kahl, Georg Bökman
arxiv.org/abs/2511.17309
Trending on www.scholar-inbox.com
SAM 3D Team, Xingyu Chen, Fu-Jen Chu ... Jitendra Malik
arxiv.org/abs/2511.16624
Trending on www.scholar-inbox.com
SAM 3D Team, Xingyu Chen, Fu-Jen Chu ... Jitendra Malik
arxiv.org/abs/2511.16624
Trending on www.scholar-inbox.com
However, for 3D tasks we show that a scaled and simplified version of multi-view MAE (which we call MuM) can outperform DINOv3, all while using orders of magnitude less compute!
TLDR; Spiritual successor to CroCo with a simpler multi-view objective and larger scale. Beats DINOv3 and CroCo v2 in RoMa, feedforward reconstruction, and rel. pose.
arxiv.org/abs/2511.17309
github.com/davnords/mum
However, for 3D tasks we show that a scaled and simplified version of multi-view MAE (which we call MuM) can outperform DINOv3, all while using orders of magnitude less compute!
Cameron Braunstein, Mariya Toneva, Eddy Ilg
arxiv.org/abs/2511.08075
Trending on www.scholar-inbox.com
Cameron Braunstein, Mariya Toneva, Eddy Ilg
arxiv.org/abs/2511.08075
Trending on www.scholar-inbox.com
Anny is built upon #MakeHuman and enables achieving SOTA performance in Human Mesh Recovery.
ArXiv: arxiv.org/abs/2511.03589
Demo: anny-demo.europe.naverlabs.com
Code: github.com/naver/anny
Anny is built upon #MakeHuman and enables achieving SOTA performance in Human Mesh Recovery.
ArXiv: arxiv.org/abs/2511.03589
Demo: anny-demo.europe.naverlabs.com
Code: github.com/naver/anny
3/3
3/3
Thanks @uni-konstanz.de Lecture Recording team 📹
🧵 2/3
Thanks @uni-konstanz.de Lecture Recording team 📹
🧵 2/3