mlsanityData to 7 Oct 2026

LOGen: Toward Lidar Object Generation by Point Diffusion

arXiv 2412.07385 ↗First posted 10 Dec 2024cs.CVcited by 9

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

Abstract (arXiv)

The generation of LiDAR scans is a growing topic with diverse applications to autonomous driving. However, scan generation remains challenging, especially when compared to the rapid advancement of image and 3D object generation. We consider the task of LiDAR object generation, requiring models to produce 3D objects as viewed by a LiDAR scan. It focuses LiDAR scan generation on a key aspect of scenes, the objects, while also benefiting from advancements in 3D object generative methods. We introduce a novel diffusion-based model to produce LiDAR point clouds of dataset objects, including intensity, and with an extensive control of the generation via conditioning information. Our experiments on nuScenes and KITTI-360 show the quality of our generations measured with new 3D metrics developed to suit LiDAR objects. The code is available at https://github.com/valeoai/LOGen.

Key facts. Cited by 9 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 51 of its 62 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

51 of 62 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer29 Jul
  2. 2024Towards Realistic Scene Generation with LiDAR Diffusion Models31 Mar
  3. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion20 Mar
  4. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generation15 Mar
  5. 2023LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models17 Sep
  6. 2022Learning to Generate Realistic LiDAR Point Clouds8 Sep
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2 Dec

Other references · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  12. 2018Demystifying MMD GANscited by 1,268
32 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  3. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  6. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  7. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  8. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  9. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  10. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  11. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
  12. 2016Revisiting Classifier Two-Sample Testscited by 258
  13. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  14. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  15. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  16. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  17. 2022CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Drivingcited by 100
  18. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 76
  19. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  20. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 65
  21. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  22. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 53
  23. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  24. 2018Augmented LiDAR Simulator for Autonomous Drivingcited by 41
  25. 2023GECCO: Geometrically-Conditioned Point Diffusion Modelscited by 24
  26. 2023Reliability in Semantic Segmentation: Can We Use Synthetic Data?cited by 24
  27. 2021EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generationcited by 21
  28. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  29. 2024Reflectivity Is All You Need!: Advancing LiDAR Semantic Segmentationcited by 9
  30. 2023Discwise Active Learning for LiDAR Semantic Segmentationcited by 7
  31. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  32. 2022Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 20253D and 4D World Modeling: A Surveycited by 64
  2. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 14
  3. 2025MObI: Multimodal Object Inpainting Using Diffusion Modelscited by 4
  4. 2025Learning to Generate 4D LiDAR Sequencescited by 2
  5. 2026R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generationcited by 2
  6. 20254D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generationcited by 0
  7. 2026Multimodal Action Diffusion for Robust End-to-End Autonomous Drivingcited by 0
  8. 2026HuLiGen: Human LiDAR Generation from Parametric Body Modelscited by 0
  9. 2026CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Simultaneous Diffusion Sampling for Conditional LiDAR Generation
  2. 2024LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes
  3. 2025DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
  4. 2024OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving
  5. 2026OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation
  6. 2025LaGen: Towards Autoregressive LiDAR Scene Generation
  7. 2021Learning to Drop Points for LiDAR Scan Synthesis
  8. 2025Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing