Search papers, labs, and topics across Lattice.
3
0
6
0
Generate realistic talking avatars 120x faster by distilling multi-step diffusion models into a single-step generator, without sacrificing quality.
Achieve flicker-free, scalable reconstruction of long dynamic videos by blending the best of stream and clip-based Gaussian Splatting.
Naive preprocessing throws away the subtle clues that reveal AI-generated videos, but processing at native resolution can expose them.
