mlsanityData to 14 Oct 2026

DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation

arXiv 2603.26263 ↗First posted 27 Mar 2026cs.CV cs.ROcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data, models trained on synthetic data often underperform on real-world data due to a data-level domain gap. To address this issue, we propose DRUM, a novel Sim2Real translation framework. We leverage a diffusion model pre-trained on unlabeled real-world data as a generative prior and translate synthetic data by reproducing two key measurement characteristics: reflectance intensity and raydrop noise. To improve sample fidelity, we introduce a raydrop-aware masked guidance mechanism that selectively enforces consistency with the input synthetic data while preserving realistic raydrop noise induced by the diffusion prior. Experimental results demonstrate that DRUM consistently improves Sim2Real performance across multiple representations of LiDAR data. The project page is available at https://miya-tomoya.github.io/drum.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 29 of its 37 references that are in the map. First posted on arXiv 27 Mar 2026.

Builds on

29 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Fast LiDAR Data Generation with Rectified Flows3 Dec
  2. 2024Towards Realistic Scene Generation with LiDAR Diffusion Models31 Mar
  3. 2023LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models17 Sep
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  9. 2021Variational Diffusion Modelscited by 1,153
  10. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  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 more
  1. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  2. 2020LiDARsim: Realistic LiDAR Simulation by Leveraging the Real Worldcited by 137
  3. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 93
  4. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 78
  5. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  6. 2018Deep Generative Modeling of LiDAR Datacited by 71
  7. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  8. 2024LidarDM: Generative LiDAR Simulation in a Generated Worldcited by 54
  9. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  10. 2021Learning to Drop Points for LiDAR Scan Synthesiscited by 27
  11. 2022Generative Range Imaging for Learning Scene Priors of 3D LiDAR Datacited by 18
  12. 2022Learning to Simulate Realistic LiDARscited by 16
  13. 2023Cosys-AirSim: A Real-Time Simulation Framework Expanded for Complex Industrial Applicationscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fast LiDAR Upsampling using Conditional Diffusion Models
  2. 2026Physics-Aware Diffusion for LiDAR Point Cloud Densification
  3. 2025Learning to Generate 4D LiDAR Sequences
  4. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generation
  5. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding
  6. 2026PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion
  7. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models
  8. 2025Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing