Search papers, labs, and topics across Lattice.
4
0
7
Forget fixed datasets: OSMa-Bench++ uses prompt-generated synthetic scenes to create controllable, extensible benchmarks for semantic mapping in robotic manipulation.
Achieve state-of-the-art zero-shot 3D visual grounding by intelligently combining geometric reasoning and on-demand image rendering, outperforming existing methods without task-specific 3D training.
Unlock real-time dynamic scene understanding: R5DGS achieves 11 FPS extrapolation by intelligently applying rigid body constraints to semantically-aware 4D Gaussians.
Semantic SLAM can now understand free-form language queries and ground them in 3D space using only a monocular video feed, opening the door to robots that truly understand and interact with the world around them.
