用扩散模型生成带强度信息的3D LiDAR点云，支持精细控制。
LOGen: Toward Lidar Object Generation by Point Diffusion
- 基于扩散模型生成带强度的LiDAR点云，支持条件控制。
- 在nuScenes和KITTI-360上生成质量优于现有方法。
- 适合自动驾驶场景模拟与数据增强研究者使用。
LiDAR扫描生成是自动驾驶领域的重要研究方向，但相较于图像和3D物体生成的发展，仍面临挑战。本文聚焦于LiDAR物体生成任务，要求模型以激光雷达视角生成3D物体点云，重点关注场景中的物体，并利用3D生成技术进展。提出一种新型基于扩散的模型，可生成包含强度信息的点云，并通过条件信息实现精细控制。在nuScenes和KITTI-360数据集上的实验表明，新提出的3D评估指标下生成效果显著。代码已开源：https://github.com/valeoai/LOGen。
原文摘要 · Abstract (English)
The generation of LiDAR scans is a growing topic with diverse applications to autonomous driving. However, scan generation remains challenging, especially when compared to the rapid advancement of image and 3D object generation. We consider the task of LiDAR object generation, requiring models to produce 3D objects as viewed by a LiDAR scan. It focuses LiDAR scan generation on a key aspect of scenes, the objects, while also benefiting from advancements in 3D object generative methods. We introduce a novel diffusion-based model to produce LiDAR point clouds of dataset objects, including intensity, and with an extensive control of the generation via conditioning information. Our experiments on nuScenes and KITTI-360 show the quality of our generations measured with new 3D metrics developed to suit LiDAR objects. The code is available at https://github.com/valeoai/LOGen.
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。