Unified Perception: Efficient Depth-Aware Video Panoptic Segmentation with Minimal Annotation Costs

no code implementations • 3 Mar 2023 • Kurt Stolle, Gijs Dubbelman

Furthermore, we show that our tracking strategies are effective for long-term object association on KITTI-STEP, achieving an STQ of 59. 1 which exceeded the performance of state-of-the-art methods that employ the same backbone network.

Depth-aware Video Panoptic Segmentation Scene Understanding +1