Proposal-Free Lidar Panoptic Segmentation With Pillar-Level Affinity

Qi Chen, Sourabh Vora; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 4529-4536

We propose a simple yet effective proposal-free architecture for lidar panoptic segmentation. We jointly optimize both semantic segmentation and class-agnostic instance classification in a single network using a pillar-based bird's-eye view representation. The instance classification head learns pairwise affinity between pillars to determine whether the pillars belong to the same instance or not. We further propose a local clustering algorithm to propagate instance ids by merging semantic segmentation and affinity predictions. Our experiments on nuScenes dataset show that our approach outperforms previous proposal-free method and is comparable to proposal-based method which requires extra annotation from object detection.