Search papers, labs, and topics across Lattice.
Center for Machine Learning, Technical University of Munich Munich
3
0
5
P-JEPA achieves state-of-the-art action classification on long procedural videos while using an order of magnitude fewer parameters than existing models.
Disentangling ego-motion from environmental dynamics allows FR3D to achieve unprecedented geometric consistency in future 3D reconstructions.
Self-supervised depth estimation gets a boost: SA4Depth aligns scene scales between pose and depth networks, leading to substantial improvements in depth prediction without sacrificing inference speed.
