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.
@article{arxiv.2412.07385,
title = {LOGen: Toward Lidar Object Generation by Point Diffusion},
author = {Ellington Kirby and Mickael Chen and Renaud Marlet and Nermin Samet},
journal= {arXiv preprint arXiv:2412.07385},
year = {2025}
}