L3DR：三维感知的激光雷达扩散与矫正
L3DR: 3D-aware LiDAR Diffusion and Rectification
针对基于距离视图的激光雷达扩散模型，提出在三维空间做点级残差回归来消除深度渗漏、波浪面等 RV 伪影，可作为即插即用后处理模块提升现有 LiDAR 生成模型的几何真实性，对自动驾驶仿真数据合成有直接价值。
原文依据 we design a 3D residual regression network that rectifies RV artifacts and achieves superb geometry realism by predicting point-level offsets in 3D space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于距离视图（RV）的激光雷达扩散近期在二维照片级真实感方面取得了巨大进展。然而，它忽略了三维几何真实性，并经常产生各种 RV 伪影，例如深度渗漏和波浪状表面。我们设计了 L3DR，一个三维感知的激光雷达扩散与矫正框架，能够在三维空间中回归并消除 RV 伪影，并准确恢复局部几何。我们的理论与实证分析表明，三维模型在生成清晰且真实的边界方面本质上优于二维模型。基于这一分析，我们设计了一个三维残差回归网络，通过在三维空间中预测点级偏移来矫正 RV 伪影并实现极佳的几何真实性。在此基础上，我们设计了一种 Welsch 损失，有助于聚焦局部几何并有效忽略异常区域。在包括 KITTI、KITTI360、nuScenes 和 Waymo 在内的多个基准上的大量实验表明，所提出的 L3DR 持续实现了最优的生成效果和更优的几何真实性。此外，L3DR 普遍适用于不同的激光雷达扩散模型，且计算开销很小。
英文原文摘要 1140 字符
Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism. However, it neglects 3D geometry realism and often generates various RV artifacts such as depth bleeding and wavy surfaces. We design L3DR, a 3D-aware LiDAR Diffusion and Rectification framework that can regress and cancel RV artifacts in 3D space and restore local geometry accurately. Our theoretical and empirical analysis reveals that 3D models are inherently superior to 2D models in generating sharp and authentic boundaries. Leveraging such analysis, we design a 3D residual regression network that rectifies RV artifacts and achieves superb geometry realism by predicting point-level offsets in 3D space. On top of that, we design a Welsch Loss that helps focus on local geometry and ignore anomalous regions effectively. Extensive experiments over multiple benchmarks including KITTI, KITTI360, nuScenes and Waymo show that the proposed L3DR achieves state-of-the-art generation and superior geometry-realism consistently. In addition, L3DR is generally applicable to different LiDAR diffusion models with little computational overhead.