mlsanityData to 14 Oct 2026

LiDPM: Rethinking Point Diffusion for Lidar Scene Completion

arXiv 2504.17791 ↗First posted 24 Apr 2025cs.CV cs.ROcited by 10

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

also in 1 more
Abstract (arXiv)

Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM .

Key facts. Cited by 10 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 32 of its 36 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

32 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models26 Sep
  2. 2024Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion20 Mar

Other references · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2022Classifier-Free Diffusion Guidancecited by 5,847
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  7. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2018PCN: Point Completion Networkcited by 384
  10. 2020Learning Gradient Fields for Shape Generationcited by 245
  11. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  12. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
18 more
  1. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
  2. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  3. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  4. 2023Neural Kernel Surface Reconstructioncited by 104
  5. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  6. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  7. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 78
  8. 2018Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentationcited by 76
  9. 2020Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Datacited by 74
  10. 20213D Semantic Scene Completion: a Surveycited by 74
  11. 2023LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDARcited by 31
  12. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  13. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  14. 2021NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Droppingcited by 16
  15. 2020Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigationcited by 13
  16. 2024Distilling Diffusion Models to Efficient 3D LiDAR Scene Completioncited by 10
  17. 2022Deep Surface Reconstruction from Point Clouds with Visibility Informationcited by 9
  18. 2023SCP: Scene Completion Pre-training for 3D Object Detectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 20253D and 4D World Modeling: A Surveycited by 67
  2. 2025La La LiDAR: Large-Scale Layout Generation from LiDAR Datacited by 10
  3. 2025LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architecturescited by 2
  4. 2026R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generationcited by 2
  5. 2026LiFlow: Flow Matching for 3D LiDAR Scene Completioncited by 2
  6. 2026Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Predictioncited by 1
  7. 2026PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completioncited by 0
  8. 2026CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domaincited by 0
  9. 2026FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flowscited by 0
  10. 2026Towards Real-Time and Adaptable LiDAR Scene Completioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Generative Semantic Scene Completion
  2. 2025Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
  3. 2024Towards Realistic Scene Generation with LiDAR Diffusion Models
  4. 2026Geometry Without Coordinates: LiDAR Diffusion as a 3D Feature Bridge
  5. 2024Fast LiDAR Upsampling using Conditional Diffusion Models
  6. 2026Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute
  7. 2025PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
  8. 2025A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation