Search papers, labs, and topics across Lattice.
The Hebrew University of Jerusalem
4
0
6
Introducing a transport-based approach that ensures stable and expressive 3D stylizations by controlling style feature allocation across multiple views.
Allocating generative capacity based on local complexity can lead to a 35% boost in synthesis quality without increasing inference costs.
Retrieval augmentation lets head avatars handle novel expressions better by mixing in similar expressions from a large unlabeled dataset during training, boosting generalization without extra labels or architecture changes.
Cycle-consistent training unlocks robust layered image decomposition in diffusion models, even with complex interactions like shading and reflections.
