mlsanityData to 7 Oct 2026

LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models

arXiv 2309.09256 ↗First posted 17 Sep 2023cs.CV cs.ROcited by 53

On the map: World models → World modeling from LiDAR generation

also in 1 more
Abstract (arXiv)

Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots, such as scalable simulation, scene manipulation, and sparse-to-dense completion of LiDAR point clouds. While existing approaches have demonstrated the feasibility of image-based LiDAR data generation using deep generative models, they still struggle with fidelity and training stability. In this work, we present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds based on the image representation of range and reflectance intensity. Our method is built upon denoising diffusion probabilistic models (DDPMs), which have shown impressive results among generative model frameworks in recent years. To effectively train DDPMs in the LiDAR domain, we first conduct an in-depth analysis of data representation, loss functions, and spatial inductive biases. Leveraging our R2DM model, we also introduce a flexible LiDAR completion pipeline based on the powerful capabilities of DDPMs. We demonstrate that our method surpasses existing methods in generating tasks on the KITTI-360 and KITTI-Raw datasets, as well as in the completion task on the KITTI-360 dataset. Our project page can be found at https://kazuto1011.github.io/r2dm.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 33 of its 44 references that are in the map. First posted on arXiv 17 Sep 2023.

Builds on

33 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data21 Oct
  2. 2022Learning to Generate Realistic LiDAR Point Clouds8 Sep
  3. 2021Learning to Drop Points for LiDAR Scan Synthesis23 Feb
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2 Dec

Other references · 29

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  10. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  11. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  12. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
17 more
  1. 2021Variational Diffusion Modelscited by 1,145
  2. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  3. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  4. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  5. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  6. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  7. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  8. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  9. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
  10. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  11. 2018Deep Generative Modeling of LiDAR Datacited by 70
  12. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  13. 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
  14. 2020Simulation-based Lidar Super-resolution for Ground Vehiclescited by 19
  15. 2021Toward Spatially Unbiased Generative Modelscited by 17
  16. 2022Implicit LiDAR Network: LiDAR Super-Resolution via Interpolation Weight Predictioncited by 14
  17. 2022CURL: Continuous, Ultra-compact Representation for LiDARcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 16; 2025: 24; 2026: 12.

53 papers.

Sort:

By area:

  1. 20253D and 4D World Modeling: A Surveycited by 64
  2. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 53
  3. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completioncited by 40
  4. 2024DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenescited by 37
  5. 2024DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulationcited by 34
  6. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 26
  7. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  8. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 14
  9. 2024Fast LiDAR Data Generation with Rectified Flowscited by 13
  10. 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusioncited by 12
  11. 2024Distilling Diffusion Models to Efficient 3D LiDAR Scene Completioncited by 10
  12. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
38 more
  1. 2024LOGen: Toward Lidar Object Generation by Point Diffusioncited by 9
  2. 2025R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Modelcited by 7
  3. 2025DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusioncited by 6
  4. 2024Taming Transformers for Realistic Lidar Point Cloud Generationcited by 5
  5. 2025Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scenecited by 5
  6. 2025Towards Generating Realistic 3D Semantic Training Data for Autonomous Drivingcited by 5
  7. 2025Veila: Panoramic LiDAR Generation from a Monocular RGB Imagecited by 5
  8. 2025U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequencescited by 5
  9. 2025OmniGen: Unified Multimodal Sensor Generation for Autonomous Drivingcited by 5
  10. 2024Just Add 100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problemcited by 4
  11. 2024Fast LiDAR Upsampling using Conditional Diffusion Modelscited by 4
  12. 2025MObI: Multimodal Object Inpainting Using Diffusion Modelscited by 4
  13. 2025Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completioncited by 4
  14. 2025A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generationcited by 4
  15. 2024Generative AI Empowered LiDAR Point Cloud Generation with Multimodal Transformercited by 3
  16. 2025COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learningcited by 2
  17. 2025SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusioncited by 2
  18. 2025Learning to Generate 4D LiDAR Sequencescited by 2
  19. 2025RadarGen: Automotive Radar Point Cloud Generation from Camerascited by 2
  20. 2026R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generationcited by 2
  21. 2026L3DR: 3D-aware LiDAR Diffusion and Rectificationcited by 2
  22. 2024Simultaneous Diffusion Sampling for Conditional LiDAR Generationcited by 1
  23. 2025LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputscited by 1
  24. 2026GEM: Generating LiDAR World Model via Deformable Mambacited by 1
  25. 2023A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systemscited by 0
  26. 2024Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Rendererscited by 0
  27. 2024Gait Sequence Upsampling using Diffusion Models for Single LiDAR Sensorscited by 0
  28. 2025PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Modelscited by 0
  29. 2025MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillationcited by 0
  30. 2025LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Drivingcited by 0
  31. 2025LaGen: Towards Autoregressive LiDAR Scene Generationcited by 0
  32. 20254D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generationcited by 0
  33. 2026Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perceptioncited by 0
  34. 2026DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentationcited by 0
  35. 2026Physics-Aware Diffusion for LiDAR Point Cloud Densificationcited by 0
  36. 2026OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generationcited by 0
  37. 2026PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completioncited by 0
  38. 2026CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domaincited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models
  2. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generation
  3. 2024Towards Realistic Scene Generation with LiDAR Diffusion Models
  4. 2025InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation
  5. 2025LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
  6. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation
  7. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models
  8. 2025LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures