Zoubin Ghahramani (@ZoubinGhahrama1)

2026-01-22 | โค๏ธ 109 | ๐Ÿ” 5


Exciting new work on detailed (pixel-level, dense) 3D visual understanding of videos. Based on a scalable feedforward architecture, itโ€™s super fast and super accurate (SOTA). Lots of uses in robotics, AR, world modellingโ€ฆ Check it out!


Tags

3D-Vision avatar