Reposted by @dustin-carrion.bsky.social
📢 [CVPR’26] Can we learn to detect, segment, and track every object in a video without human supervision?
Yes, we introduce VideoCUPS, the first unsupervised video panoptic segmentation (VPS) method: 1. Get pseudo-labels from monocular videos. 2. Train a VPS model on them.
