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

• URL: http://arxiv.org/abs/2504.08361v1
• Date: Fri, 11 Apr 2025 08:51:23 GMT
• Title: SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis
• Authors: Yi Chen, Tianchen Deng, Wentao Zhao, Xiaoning Wang, Wenqian Xi, Weidong Chen, Jingchuan Wang,
• Abstract summary: We propose SN-LiDAR, a method that jointly performs accurate semantic segmentation, high-quality geometric reconstruction, and realistic LiDAR synthesis.<n>Specifically, we employ a coarse-to-fine planar-grid feature representation to extract global features from multi-frame point clouds.<n>Experiments on Semantic KITTI and KITTI-360 demonstrate the superiority of SN-LiDAR in both semantic and geometric reconstruction.
• Score: 11.615282010184917
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining [62.433137130087445]
  SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs. We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions. With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
  arXiv  Detail & Related papers  (2025-03-25T17:59:57Z)
• GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction [12.293953058837653]
  We propose a unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field. Experiments demonstrate superior reconstruction accuracy and rendering quality across diverse trajectories.
  arXiv  Detail & Related papers  (2025-03-13T08:53:38Z)
• GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting [3.376357029373187]
  GS-LiDAR is a novel framework for generating realistic LiDAR point clouds with panoramic Gaussian splatting.<n>We introduce a novel panoramic rendering technique with explicit ray-splat intersection, guided by panoramic LiDAR supervision.
  arXiv  Detail & Related papers  (2025-01-22T11:21:20Z)
• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting [50.808933338389686]
  We present LiDAR-GS, a real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes.<n>The method achieves state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets.
  arXiv  Detail & Related papers  (2024-10-07T15:07:56Z)
• LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis [11.395101473757443]
  We propose LiDAR4D, a differentiable LiDAR-only framework for novel space-time LiDAR view synthesis. In consideration of the sparsity and large-scale characteristics, we design a 4D hybrid representation combined with multi-planar and grid features. For the realistic synthesis of LiDAR point clouds, we incorporate the global optimization of ray-drop probability to preserve cross-region patterns.
  arXiv  Detail & Related papers  (2024-04-03T13:39:29Z)
• Neural LiDAR Fields for Novel View Synthesis [80.45307792404685]
  We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements. NFL combines the rendering power of neural fields with a detailed, physically motivated model of the LiDAR sensing process. We show that the improved realism of the synthesized views narrows the domain gap to real scans and translates to better registration and semantic segmentation performance.
  arXiv  Detail & Related papers  (2023-05-02T17:55:38Z)
• LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields [112.62936571539232]
  We introduce a new task, novel view synthesis for LiDAR sensors. Traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views. We use a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points.
  arXiv  Detail & Related papers  (2023-04-20T15:44:37Z)
• StarNet: Style-Aware 3D Point Cloud Generation [82.30389817015877]
  StarNet is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network. Our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-03-28T08:21:44Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.