SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yi, Deng, Tianchen, Zhao, Wentao, Wang, Xiaoning, Xi, Wenqian, Chen, Weidong, Wang, Jingchuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909575449411584
author Chen, Yi
Deng, Tianchen
Zhao, Wentao
Wang, Xiaoning
Xi, Wenqian
Chen, Weidong
Wang, Jingchuan
author_facet Chen, Yi
Deng, Tianchen
Zhao, Wentao
Wang, Xiaoning
Xi, Wenqian
Chen, Weidong
Wang, Jingchuan
contents Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial for many downstream applications such as autonomous driving and robotic perception. Unlike images, which benefit from powerful segmentation models, LiDAR point clouds lack such large-scale pre-trained models, making semantic annotation time-consuming and labor-intensive. To address this challenge, we propose SN-LiDAR, a method that jointly performs accurate semantic segmentation, high-quality geometric reconstruction, and realistic LiDAR synthesis. Specifically, we employ a coarse-to-fine planar-grid feature representation to extract global features from multi-frame point clouds and leverage a CNN-based encoder to extract local semantic features from the current frame point cloud. Extensive experiments on SemanticKITTI and KITTI-360 demonstrate the superiority of SN-LiDAR in both semantic and geometric reconstruction, effectively handling dynamic objects and large-scale scenes. Codes will be available on https://github.com/dtc111111/SN-Lidar.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
Chen, Yi
Deng, Tianchen
Zhao, Wentao
Wang, Xiaoning
Xi, Wenqian
Chen, Weidong
Wang, Jingchuan
Computer Vision and Pattern Recognition
Robotics
Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial for many downstream applications such as autonomous driving and robotic perception. Unlike images, which benefit from powerful segmentation models, LiDAR point clouds lack such large-scale pre-trained models, making semantic annotation time-consuming and labor-intensive. To address this challenge, we propose SN-LiDAR, a method that jointly performs accurate semantic segmentation, high-quality geometric reconstruction, and realistic LiDAR synthesis. Specifically, we employ a coarse-to-fine planar-grid feature representation to extract global features from multi-frame point clouds and leverage a CNN-based encoder to extract local semantic features from the current frame point cloud. Extensive experiments on SemanticKITTI and KITTI-360 demonstrate the superiority of SN-LiDAR in both semantic and geometric reconstruction, effectively handling dynamic objects and large-scale scenes. Codes will be available on https://github.com/dtc111111/SN-Lidar.
title SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2504.08361