Search papers, labs, and topics across Lattice.
4
1
3
Reconstructing dynamic hand-object interactions from monocular video can be 6x faster and significantly more accurate by ditching heavy neural representations for a revived Sum-of-Gaussians approach.
Event cameras can now enable significantly more accurate and stable egocentric 3D human pose estimation, thanks to a novel state machine approach that directly leverages fine-grained event dynamics.
Unlock interactive digital twins from messy, real-world videos: FunRec automatically turns egocentric RGB-D recordings into simulation-ready 3D scenes.
Unlock real-world embodied AI: EmbodMocap's affordable dual-iPhone setup captures scene-aware human motion data, enabling robots to learn from human actions in everyday environments.
