Search papers, labs, and topics across Lattice.
3
0
4
3
Implicit semantic guidance in UniVVT outperforms traditional geometric preprocessing, setting a new standard for high-fidelity video virtual try-on.
Finally, generate 3D assets with application-specific, semantically meaningful parts, ready for animation and physics, without manual intervention.
Universal image editing models are surprisingly competitive with specialized virtual try-on systems, but still stumble when handling multiple garments simultaneously.
