arXiv cs.CV
· Papers
DVPSFormer: Efficient Online Depth-aware Video Panoptic Segmentation for Autonomous Driving
arXiv:2607.26165v1 Announce Type: new Abstract: Safe autonomous navigation requires a holistic understanding of dynamic environments, necessitating the simultaneous estimation of metric depth, semantic segmentation, and instance trajectories. While depth-aware video panoptic segmentation (DVPS) unifies these tasks, exi