Search papers, labs, and topics across Lattice.
3
0
4
2
NEO achieves visually coherent and geometrically consistent scene edits that significantly enhance robotic manipulation capabilities, outperforming state-of-the-art methods.
Depth-aware distillation boosts visual place recognition in forests, revealing that geometric cues can dramatically enhance model robustness against appearance variations.
Current vision models falter in natural environments, with the WildCross benchmark revealing critical gaps in depth estimation capabilities.
