mlsanityData to 7 Oct 2026

SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances

arXiv 2002.09147 ↗First posted 21 Feb 2020cs.RO cs.CV eess.IVcited by 123

Not on the map. Why?

Abstract (arXiv)

3D semantic segmentation is one of the key tasks for autonomous driving system. Recently, deep learning models for 3D semantic segmentation task have been widely researched, but they usually require large amounts of training data. However, the present datasets for 3D semantic segmentation are lack of point-wise annotation, diversiform scenes and dynamic objects. In this paper, we propose the SemanticPOSS dataset, which contains 2988 various and complicated LiDAR scans with large quantity of dynamic instances. The data is collected in Peking University and uses the same data format as SemanticKITTI. In addition, we evaluate several typical 3D semantic segmentation models on our SemanticPOSS dataset. Experimental results show that SemanticPOSS can help to improve the prediction accuracy of dynamic objects as people, car in some degree. SemanticPOSS will be published at urlwww.poss.pku.edu.cn.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 17; 2023: 29; 2024: 27; 2025: 31; 2026: 11.

123 papers.

Sort:

By area:

  1. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  2. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  3. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  4. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  5. 20213D Semantic Scene Completion: a Surveycited by 74
  6. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  7. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  8. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  9. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  10. 2022CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Drivingcited by 56
  11. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  12. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
38 more
  1. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  2. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  3. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 46
  4. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  5. 2022MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environmentscited by 40
  6. 2021GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Networkcited by 37
  7. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  8. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  9. 2023LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDARcited by 31
  10. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 29
  11. 2021Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mappingcited by 25
  12. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  13. 2023BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Cloudscited by 24
  14. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  15. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  16. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  17. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  18. 2021MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understandingcited by 22
  19. 2022SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpointscited by 22
  20. 2023Open-sourced Data Ecosystem in Autonomous Driving: the Present and Futurecited by 22
  21. 2023Novel Class Discovery for 3D Point Cloud Semantic Segmentationcited by 21
  22. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  23. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  24. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  25. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  26. 2023Benchmarking the Robustness of LiDAR Semantic Segmentation Modelscited by 18
  27. 2023WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environmentscited by 16
  28. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  29. 2023A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Servicescited by 14
  30. 2023LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptationcited by 14
  31. 2023TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentationcited by 13
  32. 2024TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sightcited by 12
  33. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  34. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  35. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  36. 2024ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentationcited by 10
  37. 2021Learning Scene Dynamics from Point Cloud Sequencescited by 9
  38. 2023Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehiclescited by 9

50 most cited of 123 All 123 (JSON)