Search papers, labs, and topics across Lattice.
4
0
5
Trajectory optimization using a spectrally-weighted FIM reduces localization error by up to 99.21%, revolutionizing UAV target tracking capabilities.
Asynchronous event cameras can achieve superior motion estimation accuracy, outperforming traditional methods by leveraging a novel minimal solver for full DoF egomotion.
Virtual-point-based solvers can dramatically improve pose estimation accuracy and efficiency in multi-camera systems, outperforming traditional methods under challenging conditions.
UniNote's two-stage training, combining contrastive SFT and RL, leapfrogs existing multimodal embeddings, delivering SOTA item-to-item retrieval performance with improved cost efficiency in real-world deployments.
