# Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion arXiv: https://arxiv.org/abs/2412.03515 ยท HTML: https://mlsanity.com/paper/2412.03515/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. - Builds on 40 of its 55 references that are in the map. - First posted on arXiv 4 Dec 2024. ## Placed in - 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 40) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020) - [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022) - [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023) - [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023) - [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016) - [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024) - [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021) - [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) - [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023) - [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023) - [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023) - [Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models](https://mlsanity.com/paper/2305.18455/) (2023) - [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020) - [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019) - [Consistency Flow Matching: Defining Straight Flows with Velocity Consistency](https://mlsanity.com/paper/2407.02398/) (2024) - [ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans](https://mlsanity.com/paper/1712.10215/) (2017) - [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023) - [UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation](https://mlsanity.com/paper/2311.01448/) (2023) - [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021) - [Towards Realistic Scene Generation with LiDAR Diffusion Models](https://mlsanity.com/paper/2404.00815/) (2024) - [Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow](https://mlsanity.com/paper/2410.07303/) (2024) - [Dense Depth Posterior (DDP) from Single Image and Sparse Range](https://mlsanity.com/paper/1901.10034/) (2019) - [LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2309.09256/) (2023) - [SemCity: Semantic Scene Generation with Triplane Diffusion](https://mlsanity.com/paper/2403.07773/) (2024) - [Confidence Propagation through CNNs for Guided Sparse Depth Regression](https://mlsanity.com/paper/1811.01791/) (2018) ## Built on by (most cited first, 10 of 10) - [LiDPM: Rethinking Point Diffusion for Lidar Scene Completion](https://mlsanity.com/paper/2504.17791/) (2025) - [La La LiDAR: Large-Scale Layout Generation from LiDAR Data](https://mlsanity.com/paper/2508.03691/) (2025) - [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025) - [Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving](https://mlsanity.com/paper/2503.21449/) (2025) - [Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2504.11447/) (2025) - [PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion](https://mlsanity.com/paper/2606.03915/) (2026) - [CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain](https://mlsanity.com/paper/2606.16048/) (2026) - [FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows](https://mlsanity.com/paper/2607.26645/) (2026) - [Towards Real-Time and Adaptable LiDAR Scene Completion](https://mlsanity.com/paper/2608.16490/) (2026) - [Generative Semantic Scene Completion](https://mlsanity.com/paper/2608.26737/) (2026) ## Abstract (arXiv) Diffusion models have been applied to 3D LiDAR scene completion due to their strong training stability and high completion quality. However, the slow sampling speed limits the practical application of diffusion-based scene completion models since autonomous vehicles require an efficient perception of surrounding environments. This paper proposes a novel distillation method tailored for 3D Li- DAR scene completion models, dubbed ScoreLiDAR, which achieves efficient yet high-quality scene completion. Score- LiDAR enables the distilled model to sample in significantly fewer steps after distillation. To improve completion quality, we also introduce a novel Structural Loss, which encourages the distilled model to capture the geometric structure of the 3D LiDAR scene. The loss contains a scene-wise term constraining the holistic structure and a point-wise term constraining the key landmark points and their relative configuration. Extensive experiments demonstrate that ScoreLiDAR significantly accelerates the completion time from 30.55 to 5.37 seconds per frame (>5x) on SemanticKITTI and achieves superior performance compared to state-of-the-art 3D LiDAR scene completion models. Our model and code are publicly available on https://github.com/happyw1nd/ScoreLiDAR.