Search papers, labs, and topics across Lattice.
2
0
3
Modeling facial deformations with a part-based neural radiance field dramatically improves the reconstruction of animatable facial avatars from monocular videos, capturing fine-grained details and generalizing to unseen expressions.
MLLMs can gain a surprising boost in 3D spatial reasoning simply by encoding 3D geometric attributes of objects as textual references indexed by unique IDs.
