CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
This addresses the need for fast and accurate scene understanding in autonomous vehicles, representing an incremental improvement over existing real-time methods.
The paper tackles the problem of achieving real-time panoptic segmentation for 3D LiDAR point clouds in autonomous driving by proposing CPSeg, which replaces proposal-based or clustering methods with a cluster-free approach and achieves state-of-the-art results among real-time methods on SemanticKITTI and nuScenes datasets.
A fast and accurate panoptic segmentation system for LiDAR point clouds is crucial for autonomous driving vehicles to understand the surrounding objects and scenes. Existing approaches usually rely on proposals or clustering to segment foreground instances. As a result, they struggle to achieve real-time performance. In this paper, we propose a novel real-time end-to-end panoptic segmentation network for LiDAR point clouds, called CPSeg. In particular, CPSeg comprises a shared encoder, a dual-decoder, and a cluster-free instance segmentation head, which is able to dynamically pillarize foreground points according to the learned embedding. Then, it acquires instance labels by finding connected pillars with a pairwise embedding comparison. Thus, the conventional proposal-based or clustering-based instance segmentation is transformed into a binary segmentation problem on the pairwise embedding comparison matrix. To help the network regress instance embedding, a fast and deterministic depth completion algorithm is proposed to calculate the surface normal of each point cloud in real-time. The proposed method is benchmarked on two large-scale autonomous driving datasets: SemanticKITTI and nuScenes. Notably, extensive experimental results show that CPSeg achieves state-of-the-art results among real-time approaches on both datasets.