mlsanityData to 7 Oct 2026

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

arXiv 2011.10033 ↗First posted 19 Nov 2020cs.CVcited by 388

Not on the map. Why?

Abstract (arXiv)

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern while maintaining these inherent properties. Moreover, a point-wise refinement module is introduced to alleviate the interference of lossy voxel-based label encoding. We evaluate the proposed model on two large-scale datasets, i.e., SemanticKITTI and nuScenes. Our method achieves the 1st place in the leaderboard of SemanticKITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%. Furthermore, the proposed 3D framework also generalizes well to LiDAR panoptic segmentation and LiDAR 3D detection.

Key facts. Cited by 388 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 64; 2023: 117; 2024: 83; 2025: 62; 2026: 28.

388 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  3. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  4. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  5. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  6. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  7. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
  8. 2023Scene as Occupancycited by 208
  9. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  10. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  11. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  12. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
38 more
  1. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  2. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  3. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  4. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  5. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  6. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  7. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  8. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  9. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  10. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  11. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  12. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  13. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  14. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  15. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 94
  16. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  17. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  18. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  19. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  20. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  21. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  22. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  23. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  24. 2023UniPAD: A Universal Pre-training Paradigm for Autonomous Drivingcited by 73
  25. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  26. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  27. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  28. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  29. 2024Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Drivingcited by 67
  30. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  31. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  32. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  33. 2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
  34. 2022Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmapcited by 59
  35. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  36. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  37. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  38. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56

50 most cited of 388 All 388 (JSON)