DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Kaiwen, Liu, Xinze, Zhou, Xia, Hu, Hengtong, Xiang, Jie, Zhang, Luyao, Zhang, Xueyang, Zhan, Kun, Zhan, Yifei, Lang, Xianpeng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918205849600000
author Cai, Kaiwen
Liu, Xinze
Zhou, Xia
Hu, Hengtong
Xiang, Jie
Zhang, Luyao
Zhang, Xueyang
Zhan, Kun
Zhan, Yifei
Lang, Xianpeng
author_facet Cai, Kaiwen
Liu, Xinze
Zhou, Xia
Hu, Hengtong
Xiang, Jie
Zhang, Luyao
Zhang, Xueyang
Zhan, Kun
Zhan, Yifei
Lang, Xianpeng
contents The generation of realistic LiDAR point clouds plays a crucial role in the development and evaluation of autonomous driving systems. Although recent methods for 3D LiDAR point cloud generation have shown significant improvements, they still face notable limitations, including the lack of sequential generation capabilities and the inability to produce accurately positioned foreground objects and realistic backgrounds. These shortcomings hinder their practical applicability. In this paper, we introduce DriveLiDAR4D, a novel LiDAR generation pipeline consisting of multimodal conditions and a novel sequential noise prediction model LiDAR4DNet, capable of producing temporally consistent LiDAR scenes with highly controllable foreground objects and realistic backgrounds. To the best of our knowledge, this is the first work to address the sequential generation of LiDAR scenes with full scene manipulation capability in an end-to-end manner. We evaluated DriveLiDAR4D on the nuScenes and KITTI datasets, where we achieved an FRD score of 743.13 and an FVD score of 16.96 on the nuScenes dataset, surpassing the current state-of-the-art (SOTA) method, UniScene, with an performance boost of 37.2% in FRD and 24.1% in FVD, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
Cai, Kaiwen
Liu, Xinze
Zhou, Xia
Hu, Hengtong
Xiang, Jie
Zhang, Luyao
Zhang, Xueyang
Zhan, Kun
Zhan, Yifei
Lang, Xianpeng
Computer Vision and Pattern Recognition
The generation of realistic LiDAR point clouds plays a crucial role in the development and evaluation of autonomous driving systems. Although recent methods for 3D LiDAR point cloud generation have shown significant improvements, they still face notable limitations, including the lack of sequential generation capabilities and the inability to produce accurately positioned foreground objects and realistic backgrounds. These shortcomings hinder their practical applicability. In this paper, we introduce DriveLiDAR4D, a novel LiDAR generation pipeline consisting of multimodal conditions and a novel sequential noise prediction model LiDAR4DNet, capable of producing temporally consistent LiDAR scenes with highly controllable foreground objects and realistic backgrounds. To the best of our knowledge, this is the first work to address the sequential generation of LiDAR scenes with full scene manipulation capability in an end-to-end manner. We evaluated DriveLiDAR4D on the nuScenes and KITTI datasets, where we achieved an FRD score of 743.13 and an FVD score of 16.96 on the nuScenes dataset, surpassing the current state-of-the-art (SOTA) method, UniScene, with an performance boost of 37.2% in FRD and 24.1% in FVD, respectively.
title DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.13309