SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
This addresses the need for semantic-aware LiDAR synthesis in applications like autonomous driving, where existing methods lack semantic reconstruction, though it is incremental as it builds on prior novel view synthesis approaches.
The paper tackles the problem of novel view synthesis for LiDAR point clouds by proposing SN-LiDAR, which jointly performs semantic segmentation, geometric reconstruction, and realistic LiDAR synthesis, achieving superior results on SemanticKITTI and KITTI-360 datasets.
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.