用扩散模型生成真实激光雷达数据，解决仿真到现实的差距问题。
DRUM: Diffusion-based Raydrop-aware Unpaired Mapping for Sim2Real LiDAR Segmentation
- 用预训练扩散模型作为先验，生成带反射强度和丢点噪声的真实数据。
- 在多个激光雷达表示上提升真实场景分割性能，显著缩小仿真与现实差距。
- 适合做自动驾驶感知、仿真数据迁移的研究者或工程师使用。
基于激光雷达的语义分割是自主移动机器人的重要组成部分，但大规模激光雷达点云标注成本高昂且耗时。尽管模拟器可提供带标签的合成数据，但仅在合成数据上训练的模型常因数据层面的域差异，在真实数据上表现不佳。为此，本文提出DRUM，一种新颖的仿真到现实（Sim2Real）转换框架。我们利用在无标签真实世界数据上预训练的扩散模型作为生成先验，通过重现两个关键测量特性——反射强度和丢点噪声——来转化合成数据。为提升样本保真度，引入一种考虑丢点的掩码引导机制，选择性地强制输入合成数据的一致性，同时保留扩散先验带来的真实丢点噪声。实验结果表明，DRUM在多种激光雷达数据表示上均持续提升仿真到现实的性能。项目主页见 https://miya-tomoya.github.io/drum。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。