Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity
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 methods and is comparable to proposal-based methods which requires extra annotation from object detection.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationClusteringobject-detectionObject DetectionPanoptic SegmentationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
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 cluste…
Autonomous DrivingClusteringDecoderDepth Completion+4Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation
Panoptic segmentation brings together two separate tasks: instance and semantic segmentation. Although they are related, unifying them faces an apparent paradox: how to learn simultaneously instance-specific and category…
Instance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationHierarchical Lovasz Embeddings for Proposal-Free Panoptic Segmentation
Panoptic segmentation brings together two separate tasks: instance and semantic segmentation. Although they are related, unifying them faces an apparent paradox: how to learn simultaneously instance-specific and cate…
Instance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationPanoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation
Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework. However, an effi…
ClusteringInstance SegmentationPanoptic SegmentationSegmentation+1Center Focusing Network for Real-Time LiDAR Panoptic Segmentation
LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time. The recent proposal-free methods accelerate the algorith…
Panoptic SegmentationSegmentation