Search papers, labs, and topics across Lattice.
Archimedes Athena Research Center Greece 2valeo.ai, University of Crete
2
0
4
2
By predicting future scene structure in the feature space of a frozen vision foundation model before rendering pixels, Re2Pix achieves state-of-the-art video prediction with improved temporal consistency and perceptual quality.
Just a handful of annotated examples can dramatically close the performance gap between zero-shot and fully supervised open-vocabulary segmentation.
