首篇综述深度学习激光雷达超分辨率，助力自动驾驶低成本高精度感知
A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving
- 按网络结构分类四类方法：CNN、深度展开、隐式表征、Transformer/Mamba
- 提出统一评估框架，涵盖数据表示、基准数据集与评测指标
- 聚焦实时推理与跨传感器泛化，适合自动驾驶系统研发人员
激光雷达是自动驾驶的关键传感器，但高分辨率设备成本高昂，而低成本低分辨率设备生成的点云稀疏，难以捕捉关键细节。激光雷达超分辨率通过深度学习技术增强稀疏点云，弥合不同传感器间的差距，实现真实场景下的跨传感器兼容性。本文首次系统综述面向自动驾驶的激光雷达超分辨率方法。我们将现有方法分为四类：基于CNN的架构、基于模型的深度展开、隐式表示方法以及基于Transformer和Mamba的方法。我们建立了基础概念，包括数据表示、问题定义、基准数据集与评估指标。当前趋势包括采用范围图像表示以提升处理效率、极端模型压缩及灵活分辨率架构的发展。近期研究重点在于实现实时推理与跨传感器泛化，以支持实际部署。最后，我们指出现存挑战与未来研究方向，推动该技术进一步发展。
原文摘要 · Abstract (English)
LiDAR sensors are often considered essential for autonomous driving, but high-resolution sensors remain expensive while affordable low-resolution sensors produce sparse point clouds that miss critical details. LiDAR super-resolution addresses this challenge by using deep learning to enhance sparse point clouds, bridging the gap between different sensor types and enabling cross-sensor compatibility in real-world deployments. This paper presents the first comprehensive survey of LiDAR super-resolution methods for autonomous driving. Despite the importance of practical deployment, no systematic review has been conducted until now. We organize existing approaches into four categories: CNN-based architectures, model-based deep unrolling, implicit representation methods, and Transformer and Mamba-based approaches. We establish fundamental concepts including data representations, problem formulation, benchmark datasets and evaluation metrics. Current trends include the adoption of range image representation for efficient processing, extreme model compression and the development of resolution-flexible architectures. Recent research prioritizes real-time inference and cross-sensor generalization for practical deployment. We conclude by identifying open challenges and future research directions for advancing LiDAR super-resolution technology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。