Search papers, labs, and topics across Lattice.
5
0
4
0
A single set of learned manipulation skills transfers to the real world with 78% success, bypassing the need for task-specific fine-tuning or re-training on real data.
An automated pipeline that converts hair-card models into high-quality strand-based hairstyles that preserves the original hairstyle while enriching it with fine-scale geometric detail and adhering to standard production requirements is presented.
RoboEdit transforms abundant human manipulation videos into high-fidelity training data for robots, unlocking new avenues for scalable robot learning.
Robot actions can serve as powerful geometric supervision, enabling sparse 3D representations that are both reusable and effective across diverse manipulation tasks.
