mlsanityData to 7 Oct 2026

World modeling from LiDAR generation

52 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: lidar, point, diffusion, generation, scene

Key facts. World modeling from LiDAR generation: 52 papers on arXiv since 2013 (data through 7 Oct 2026). 27 of its 52 mapped papers (52%) cite “Learning to Generate Realistic LiDAR Point Clouds” (2022, arXiv 2209.03954). 25 of its 52 mapped papers (48%) cite “LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models” (2023, arXiv 2309.09256). 1 new paper 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

1 new since 17 Sep

  1. TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception also fits: World models for autonomous driving

Foundations

Most cited by papers here

  1. Learning to Generate Realistic LiDAR Point Clouds2022cited by 27 here
  2. LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models2023cited by 25 here
  3. Towards Realistic Scene Generation with LiDAR Diffusion Models2024cited by 23 here
  4. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2016cited by 20 here
  5. RangeLDM: Fast Realistic LiDAR Point Cloud Generation2024cited by 15 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 20 here
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 13 here
  3. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 27 here
  4. 2023LiDAR Data Synthesis with Denoising Diffusion Probabilistic Modelscited by 25 here
  5. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completioncited by 12 here
  6. 2024DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenescited by 6 here
  7. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 5 here
17 more it builds on, not in this chain
  1. 2017CARLA: An Open Urban Driving Simulatorcited by 13 here
  2. 2020Denoising Diffusion Probabilistic Modelscited by 29 here
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 5 here
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 10 here
  5. 2021Learning to Drop Points for LiDAR Scan Synthesiscited by 11 here
  6. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 11 here
  7. 2022Generative Range Imaging for Learning Scene Priors of 3D LiDAR Datacited by 8 here
  8. 2022Scalable Diffusion Models with Transformerscited by 12 here
  9. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 8 here
  10. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 5 here
  11. 2023Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusioncited by 5 here
  12. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 6 here
  13. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 15 here
  14. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 23 here
  15. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 12 here
  16. 2024Fast LiDAR Data Generation with Rectified Flowscited by 8 here
  17. 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusioncited by 7 here

The 24 most cited of 85.

Browse

30 of 52, ranked 6–35

  1. 6PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space201713
  2. 7Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion202412
  3. 8Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer202412
  4. 9Learning to Drop Points for LiDAR Scan Synthesis202111
  5. 10Fast LiDAR Data Generation with Rectified Flows20248
  6. 11Rethinking Range View Representation for LiDAR Segmentation20238
  7. 12Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data20228
  8. 13WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion20257
  9. 14SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding20255
  10. 15LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences20255
All 30
  1. 16Perspective-Invariant 3D Object Detection20254
  2. 17OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving20244
  3. 18LiDPM: Rethinking Point Diffusion for Lidar Scene Completion20253
  4. 19Veila: Panoramic LiDAR Generation from a Monocular RGB Image20253
  5. 20DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models20243
  6. 21LOGen: Toward Lidar Object Generation by Point Diffusion20243
  7. 22Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks20212
  8. 23Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks20152
  9. 24Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion20251
  10. 25Towards foundational LiDAR world models with efficient latent flow matching20251
  11. 26Learning to Generate 4D LiDAR Sequences20251
  12. 27U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences20251
  13. 28Taming Transformers for Realistic Lidar Point Cloud Generation20241
  14. 29X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios20241
  15. 30TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers20221
  16. 31Rich feature hierarchies for accurate object detection and semantic segmentation20131
  17. 32R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation20260
  18. 33L3DR: 3D-aware LiDAR Diffusion and Rectification20260
  19. 34GEM: Generating LiDAR World Model via Deformable Mamba20260
  20. 35OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation20260