mlsanityData to 7 Oct 2026

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

arXiv 2012.03762 ↗First posted 7 Dec 2020cs.CVcited by 222

Not on the map. Why?

Abstract (arXiv)

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

Key facts. Cited by 222 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 21; 2023: 60; 2024: 62; 2025: 44; 2026: 22.

222 papers.

Sort:

By area:

  1. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  3. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  4. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  5. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  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. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  9. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  10. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  11. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  12. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
38 more
  1. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  2. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  3. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  4. 2024UniScene: Unified Occupancy-centric Driving Scene Generationcited by 102
  5. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  6. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 94
  7. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 88
  8. 2023NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Spacecited by 88
  9. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  10. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  11. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  12. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  13. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 76
  14. 20213D Semantic Scene Completion: a Surveycited by 74
  15. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  16. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  17. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  18. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  19. 2024Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Drivingcited by 67
  20. 2021Box-Aware Feature Enhancement for Single Object Tracking on Point Cloudscited by 66
  21. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 66
  22. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  23. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  24. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  25. 2022Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 55
  26. 2022LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detectioncited by 54
  27. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  28. 2024SemCity: Semantic Scene Generation with Triplane Diffusioncited by 53
  29. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
  30. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  31. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  32. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  33. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 46
  34. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  35. 2024MonoOcc: Digging into Monocular Semantic Occupancy Predictioncited by 43
  36. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  37. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  38. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41

50 most cited of 222 All 222 (JSON)