Search papers, labs, and topics across Lattice.
4
4
6
By disentangling camera-space estimation from world-space refinement via dual diffusion models, DuoMo achieves state-of-the-art human motion reconstruction from noisy video, bypassing the limitations of parametric models.
Finally, digital humans can have realistic, socially aware conversations: DyaDiT generates dyadic gestures that users strongly prefer over existing methods.
Robots can now perform intricate assembly tasks and recover from errors in real-time, without any training, by fusing vision-language models with video-based kinematic priors for action planning.
Forget clunky skeletons: this new model lets you prompt your way to accurate 3D human meshes from single images, even in the wildest poses.
