mlsanityData to 14 Oct 2026

Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data

arXiv 2210.11750 ↗First posted 21 Oct 2022cs.CV cs.RO eess.IVcited by 18

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

Abstract (arXiv)

3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular resolution and missing properties. Existing studies have tackled the issue by learning inter-domain mapping, while the transferability is constrained by the training configuration and the training is susceptible to peculiar lossy noises called ray-drop. To address the issue, this paper proposes a generative model of LiDAR range images applicable to the data-level domain transfer. Motivated by the fact that LiDAR measurement is based on point-by-point range imaging, we train an implicit image representation-based generative adversarial networks along with a differentiable ray-drop effect. We demonstrate the fidelity and diversity of our model in comparison with the point-based and image-based state-of-the-art generative models. We also showcase upsampling and restoration applications. Furthermore, we introduce a Sim2Real application for LiDAR semantic segmentation. We demonstrate that our method is effective as a realistic ray-drop simulator and outperforms state-of-the-art methods.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 40 of its 53 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

40 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021Learning to Drop Points for LiDAR Scan Synthesis23 Feb
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space7 Jun
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2 Dec

Other references · 37

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  12. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
25 more
  1. 2018Demystifying MMD GANscited by 1,293
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  4. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  5. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  7. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  8. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  9. 2021GAN Inversion: A Surveycited by 367
  10. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  11. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  12. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  13. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  14. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  15. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  16. 2020Adversarial Generation of Continuous Imagescited by 135
  17. 2016Invertible Conditional GANs for image editingcited by 118
  18. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  19. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
  20. 2019HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptationcited by 89
  21. 2018Deep Generative Modeling of LiDAR Datacited by 71
  22. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  23. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 47
  24. 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
  25. 2019Noise Robust Generative Adversarial Networkscited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 9; 2025: 4; 2026: 2.

18 papers.

Sort:

By area:

  1. 20253D and 4D World Modeling: A Surveycited by 67
  2. 2023LiDAR Data Synthesis with Denoising Diffusion Probabilistic Modelscited by 55
  3. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 54
  4. 2024DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenescited by 38
  5. 2024Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformercited by 27
  6. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 26
  7. 2024Fast LiDAR Data Generation with Rectified Flowscited by 14
  8. 2025WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusioncited by 12
  9. 2024Taming Transformers for Realistic Lidar Point Cloud Generationcited by 5
  10. 2024Fast LiDAR Upsampling using Conditional Diffusion Modelscited by 4
  11. 2026L3DR: 3D-aware LiDAR Diffusion and Rectificationcited by 3
  12. 2025SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusioncited by 2
6 more
  1. 2023Differentiable SLAM Helps Deep Learning-based LiDAR Perception Taskscited by 1
  2. 2024A Probabilistic Formulation of LiDAR Mapping with Neural Radiance Fieldscited by 1
  3. 2025LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputscited by 1
  4. 2023A Unified Generative Framework for Realistic Lidar Simulation in Autonomous Driving Systemscited by 0
  5. 2024Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Rendererscited by 0
  6. 2026DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generation
  2. 2023Rethinking Range View Representation for LiDAR Segmentation
  3. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding
  4. 2026Adversarially Guided Diffusion for LiDAR Range Image Synthesis
  5. 2025Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing
  6. 2024Simultaneous Diffusion Sampling for Conditional LiDAR Generation
  7. 2026OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation
  8. 2022Learning to Generate Realistic LiDAR Point Clouds