# Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

arXiv: https://arxiv.org/abs/2403.13470 · HTML: https://mlsanity.com/paper/2403.13470/

## Key facts

- Cited by 40 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 44 of its 54 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Placed in

- World models / [World modeling from LiDAR generation](https://mlsanity.com/wm/world-modeling-from-lidar-generation/)
- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 44)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation](https://mlsanity.com/paper/2110.02624/) (2021)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking](https://mlsanity.com/paper/2109.03805/) (2021)
- [Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image](https://mlsanity.com/paper/1709.07492/) (2017)
- [Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.14704/) (2022)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way](https://mlsanity.com/paper/2209.15397/) (2022)

## Built on by (most cited first, 30 of 40)

- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes](https://mlsanity.com/paper/2410.18084/) (2024)
- [SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization](https://mlsanity.com/paper/2503.14558/) (2025)
- [DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2409.18092/) (2024)
- [Diffusion Models in 3D Vision: A Survey](https://mlsanity.com/paper/2410.04738/) (2024)
- [GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting](https://mlsanity.com/paper/2507.19451/) (2025)
- [Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2412.03515/) (2024)
- [OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation](https://mlsanity.com/paper/2412.11183/) (2024)
- [LiDPM: Rethinking Point Diffusion for Lidar Scene Completion](https://mlsanity.com/paper/2504.17791/) (2025)
- [Towards foundational LiDAR world models with efficient latent flow matching](https://mlsanity.com/paper/2506.23434/) (2025)
- [LOGen: Toward Lidar Object Generation by Point Diffusion](https://mlsanity.com/paper/2412.07385/) (2024)
- [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025)
- [Towards Learning to Complete Anything in Lidar](https://mlsanity.com/paper/2504.12264/) (2025)
- [Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving](https://mlsanity.com/paper/2503.21449/) (2025)
- [LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes](https://mlsanity.com/paper/2412.00592/) (2024)
- [Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2504.11447/) (2025)
- [DOC-Depth: A novel approach for dense depth ground truth generation](https://mlsanity.com/paper/2502.02144/) (2025)
- [L3DR: 3D-aware LiDAR Diffusion and Rectification](https://mlsanity.com/paper/2602.19064/) (2026)
- [Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models](https://mlsanity.com/paper/2501.01761/) (2025)
- [Scene Coordinate Reconstruction Priors](https://mlsanity.com/paper/2510.12387/) (2025)
- [LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures](https://mlsanity.com/paper/2511.10209/) (2025)
- [R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation](https://mlsanity.com/paper/2601.07692/) (2026)
- [LiFlow: Flow Matching for 3D LiDAR Scene Completion](https://mlsanity.com/paper/2602.02232/) (2026)
- [Simultaneous Diffusion Sampling for Conditional LiDAR Generation](https://mlsanity.com/paper/2410.11628/) (2024)
- [Map Imagination Like Blind Humans: Group Diffusion Model for Robotic Map Generation](https://mlsanity.com/paper/2412.16908/) (2024)
- [Real-Time LiDAR Super-Resolution via Frequency-Aware Multi-Scale Fusion](https://mlsanity.com/paper/2511.07377/) (2025)
- [Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion](https://mlsanity.com/paper/2511.16161/) (2025)
- [TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba](https://mlsanity.com/paper/2503.13004/) (2025)
- [PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models](https://mlsanity.com/paper/2508.17050/) (2025)
- [4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation](https://mlsanity.com/paper/2512.14235/) (2025)

## Abstract (arXiv)

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point clouds from the scene. However, compared to human perception, such systems struggle to deduce the unseen parts of the scene given those sparse point clouds. In this matter, the scene completion task aims at predicting the gaps in the LiDAR measurements to achieve a more complete scene representation. Given the promising results of recent diffusion models as generative models for images, we propose extending them to achieve scene completion from a single 3D LiDAR scan. Previous works used diffusion models over range images extracted from LiDAR data, directly applying image-based diffusion methods. Distinctly, we propose to directly operate on the points, reformulating the noising and denoising diffusion process such that it can efficiently work at scene scale. Together with our approach, we propose a regularization loss to stabilize the noise predicted during the denoising process. Our experimental evaluation shows that our method can complete the scene given a single LiDAR scan as input, producing a scene with more details compared to state-of-the-art scene completion methods. We believe that our proposed diffusion process formulation can support further research in diffusion models applied to scene-scale point cloud data.