Search papers, labs, and topics across Lattice.
5
1
6
1
Achieving state-of-the-art lip-sync accuracy while maintaining natural expressiveness, ReFree-S2V redefines the standards for speech-driven character animation.
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.
Unlock interactive digital twins from messy, real-world videos: FunRec automatically turns egocentric RGB-D recordings into simulation-ready 3D scenes.
Finally, realistic and expressive full-body gestures for conversational agents can be generated in real-time, thanks to a novel causal framework that models both temporal dynamics and part-level motion hierarchy.
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.
