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

• URL: http://arxiv.org/abs/2603.26263v1
• Date: Fri, 27 Mar 2026 10:30:49 GMT
• Title: DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation
• Abstract summary: DRUM is a novel Sim2Real translation framework.<n>We leverage a diffusion model pre-trained on unlabeled real-world data as a generative prior.<n>We introduce a raydrop-aware masked guidance mechanism that selectively enforces consistency with the input synthetic data.
• Score: 3.8498574327875947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data [61.62554324594797]
  We propose DreamMask, which explores how to generate training data in the open-vocabulary setting, and how to train the model with both real and synthetic data.<n>In general, DreamMask significantly simplifies the collection of large-scale training data, serving as a plug-and-play enhancement for existing methods.<n>For instance, when trained on COCO and tested on ADE20K, the model equipped with DreamMask outperforms the previous state-of-the-art by a substantial margin of 2.1% mIoU.
  arXiv  Detail & Related papers  (2025-01-03T19:00:00Z)
• Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonar [1.7851018240619703]
  This paper proposes a Syn2Real (Synthetic to Real) domain generalization approach using diffusion models to address this challenge. We demonstrate that synthetic data generated with noise by DDPM and DDIM models, even if not perfectly realistic, can effectively augment real-world samples for training.
  arXiv  Detail & Related papers  (2024-10-16T18:42:08Z)
• Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection [45.102312149413855]
  We study the synthesis-based LiDAR data augmentation approach (so-called GT-Aug) which offers maxium controllability over generated data samples. We propose Real-Aug, a synthesis-based augmentation method which prioritizes on generating realistic LiDAR scans. We achieve a state-of-the-art 0.744 NDS and 0.702 mAP on nuScenes test set.
  arXiv  Detail & Related papers  (2023-05-22T09:24:55Z)
• Synthetic data, real errors: how (not) to publish and use synthetic data [86.65594304109567]
  We show how the generative process affects the downstream ML task. We introduce Deep Generative Ensemble (DGE) to approximate the posterior distribution over the generative process model parameters.
  arXiv  Detail & Related papers  (2023-05-16T07:30:29Z)
• A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation [42.2398858786125]
  Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. The uncontrollable data collection process produces non-IID training and test data, where undesired duplication may exist. To circumvent them, an alternative is to generate synthetic data via 3D rendering with domain randomization.
  arXiv  Detail & Related papers  (2023-03-16T09:03:52Z)
• Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation [69.1351513309953]
  We show that accurately simulating the low-frequency components of Room Impulse Responses (RIRs) is important to achieving good dereverberation. We demonstrate that speech dereverberation models trained on hybrid synthetic RIRs outperform models trained on RIRs generated by prior geometric ray tracing methods.
  arXiv  Detail & Related papers  (2022-12-10T20:15:23Z)
• PCGen: Point Cloud Generator for LiDAR Simulation [10.692184635629792]
  Existing methods generate data which are more noisy and complete than the real point clouds. We propose FPA raycasting and surrogate model raydrop. With minimal training data, the surrogate model can generalize to different geographies and scenes. Results show that object detection models trained by simulation data can achieve similar result as the real data trained model.
  arXiv  Detail & Related papers  (2022-10-17T04:13:21Z)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.