NIDAR：用于可扩展场景无关的LiDAR强度重建的近红外引导的内在分解
NIDAR: NIR-Guided Intrinsic Decomposition for Scalable Scene-Agnostic LiDAR Intensity Reconstruction
浏览论文内容
中文总结 AI 辅助
NIDAR提出一种前馈框架，利用预训练伪近红外转换和层次化内在分解，从RGB和几何合成LiDAR强度，无需目标场景标签，在Waymo和nuScenes上验证了有效性和可扩展性。
中文摘要 AI 辅助
LiDAR回波强度为机器人感知和状态估计提供了互补的表面响应线索，然而许多仿真流程要么忽略它，要么使用需要真实强度监督和逐场景优化的重建方法来再现它。这些要求增加了数据采集和拟合成本，并限制了其在模拟场景中的复用。我们提出了NIDAR，一个前馈框架，能够从RGB外观和模拟器几何中合成密集的强度类观测。NIDAR结合了预训练的伪近红外转换、层次化内在分解、几何感知调制和源域分布校准，将反射率相关的图像线索迁移到模拟点云。其学习组件使用Waymo数据离线训练；在Waymo和nuScenes上进行评估时，其权重和校准保持固定。因此，部署既不需要目标场景的强度标签，也不需要目标场景的基于梯度的拟合。所报告的比较显示，与评估的重建基线相比，在像素级精度上具有竞争力，在结构和感知保真度上表现良好。一项受控的伪近红外与RGB对比诊断进一步表明，当通过论文对齐的反射率和重映射路径使用时，伪近红外先验最为有益，而不是作为简单的直接强度回归器。我们进一步将NIDAR与Unreal Engine 5、Isaac Sim以及一个生成式LiDAR流程集成。在两个模拟室内场景中评估的两个强度感知SLAM系统表明了潜在的下游实用性，但并不构成真实机器人验证。因此，NIDAR为所评估的设置提供了一种可扩展的强度合成接口；跨波长、相机配置、嵌入式以及真实传感器验证仍是未来工作。
英文摘要
LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it or reproduce it using reconstruction methods that require real intensity supervision and per-scene optimization. These requirements increase data-collection and fitting costs and limit reuse across simulated scenes. We present NIDAR, a feed-forward framework that synthesizes dense intensity-like observations from RGB appearance and simulator geometry. NIDAR combines pretrained pseudo-NIR translation, hierarchical intrinsic decomposition, geometry-aware modulation, and source-domain distribution calibration to transfer reflectance-related image cues to simulated point clouds. Its learned components are trained offline using Waymo data; their weights and calibration remain fixed during evaluation on Waymo and nuScenes. Deployment therefore requires neither target-scene intensity labels nor target-scene gradient-based fitting. The reported comparisons show competitive pixel-wise accuracy and favorable structural and perceptual fidelity against the evaluated reconstruction baselines. A controlled pseudo-NIR-versus-RGB diagnostic further shows that the pseudo-NIR prior is most beneficial when used through the paper-aligned reflectance-and-remapping route, rather than as a simple direct intensity regressor. We further integrate NIDAR with Unreal Engine 5, Isaac Sim, and a generative LiDAR pipeline. Two intensity-aware SLAM systems evaluated in two simulated indoor scenes suggest potential downstream utility, but do not constitute real-robot validation. NIDAR therefore offers a scalable intensity-synthesis interface for the evaluated settings; cross-wavelength, camera-configuration, embedded, and real-sensor validation remain future work.
发表机构
- Chongqing University（重庆大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
