Search papers, labs, and topics across Lattice.
3
0
6
56
Unlock 36% better video depth estimation and 20% better camera pose estimation by simply letting your model learn from its own unlabeled video predictions.
Human-level 3D perception can emerge from a surprisingly simple, scalable learning objective using multi-view images, finally closing the gap between AI and human performance on this fundamental visual task.
Humanoid robots can now perform vision-based parkour, chaining together dynamic skills like climbing, vaulting, and rolling, adapting to real-time obstacle changes.
