Search papers, labs, and topics across Lattice.
2
0
4
By aligning image and LiDAR features to event-derived spatiotemporal edges, $x^2$-Fusion achieves state-of-the-art accuracy in optical and scene flow estimation, particularly under challenging conditions where other multimodal fusion methods falter.
Generative video codecs can now run at 150 FPS on smartphones, thanks to a hybrid approach that makes traditional codecs and neural nets work together.