PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation

Reliable LiDAR panoptic segmentation (LPS), including both semantic and instance segmentation, is vital for many robotic applications, such as autonomous driving. This work proposes a new LPS framework named PANet to eliminate the dependency on the offset branch and improve the performance on large objects, which are always over-segmented by clustering algorithms. Firstly, we propose a non-learning Sparse Instance Proposal (SIP) module with the “sampling-shifting-grouping” scheme to directly group thing points into instances from the raw point cloud efficiently. More specifically, balanced point sampling is introduced to generate sparse seed points with more uniform point distribution over the distance range. And a shift module, termed bubble shifting, is proposed to shrink the seed points to the clustered centers. Then we utilize the connected component label algorithm to generate instance proposals. Furthermore, an instance aggregation module is devised to integrate potentially fragmented instances, improving the performance of the SIP module on large objects. Extensive experiments show that PANet achieves state-of-the-art performance among published works on the SemanticKITII validation and nuScenes validation for the panoptic segmentation task. Code is available at https://github.com/Jieqianyu/PANet.git.

Authors

• Jianbiao Mei
• Yu Yang
• Mengmeng Wang 0005
• Xiaojun Hou
• Laijian Li
• Yong Liu 0007

Keywords

• Point cloud compression
• Training
• Instance segmentation
• Laser radar
• Semantics
• Clustering algorithms
• Proposals
• Panoptic Segmentation
• LiDAR Panoptic Segmentation
• Uniform Distribution
• Clustering Algorithm
• Extensive Experiments
• Point Cloud
• Semantic Segmentation
• Distance Range
• Large Objects
• Robotic Applications
• Raw Point
• Aggregation Module
• Raw Point Cloud
• Random Sampling
• K-nearest Neighbor
• Global Features
• Majority Voting
• Computational Overhead
• Voxel-based Methods
• Minimum Radius
• Clustering-based Methods
• 2D Feature
• Segmentation Performance
• 3D Object Detection
• LiDAR Point Clouds
• Weak Connections
• Multi-scale Features