REALM: An RGB and Event Aligned Latent Manifold for Cross-Modal Perception
This work proposes REALM, a cross-modal framework that learns an RGB- and Event-Aligned Latent Manifold by projecting event representations into the pretrained latent space of RGB foundation models, and demonstrates state-of-the-art performance in wide-baseline feature matching, significantly outperforming specialized...
Vincenzo Polizzi, David B. Lindell, Jonathan Kelly
· arXiv.org · 0 citations