Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
1
A single model now masters 3D hand reconstruction, predicts future video under actions, and plans complex manipulation sequences from language, outperforming specialized methods.
Given multiple input images, this work predicts a point cloud in canonical space, deterministically inject the predicted geometry into the diffusion process through noise inversion, and modulate the resulting noise to preserve the generative flexibility required to complete unobserved regions and refine visible geometry.