Search papers, labs, and topics across Lattice.
Affiliation:
5
0
6
1
ParticleSplat is presented, a self-supervised object-centric learning method that decomposes scenes into a set of latent particles representing semantic entities through feedforward 3D Gaussian Splatting, and it is established that the learned 3D representation improves downstream performance on robotic manipulation tasks.
Grasp datasets can revolutionize robotic dexterity, enabling significant improvements in articulated tool use performance.
Manipulating 3D latent particles can generate novel scene configurations, revolutionizing how we approach object-centric representation in robotics.
Hierarchical sub-goal policies enable robots to adapt to novel tasks with just a few human demonstrations, significantly enhancing their manipulation capabilities.
Disentangling object geometry from placement frame diffusion yields surprisingly high accuracy in robotic manipulation, even surpassing SE(3)-diffusion methods.
