Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving

June Moh Goo, Zichao Zeng, Jan Boehm

TL;DR

This paper presents the first comprehensive survey of LiDAR super-resolution methods for autonomous driving, establishing fundamental concepts including data representations, problem formulation, benchmark datasets and evaluation metrics.

Abstract

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.

A Comprehensive Survey on Deep Learning-Based LiDAR Super-Resolution for Autonomous Driving

TL;DR

This paper presents the first comprehensive survey of LiDAR super-resolution methods for autonomous driving, establishing fundamental concepts including data representations, problem formulation, benchmark datasets and evaluation metrics.

Abstract

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.
Paper Structure (26 sections, 14 equations, 1 figure, 2 tables)

This paper contains 26 sections, 14 equations, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Backgrounds and Preliminaries
  3. LiDAR Point Cloud Representation
  4. Problem Formulation
  5. Evaluation Metrics
  6. Benchmark Datasets
  7. Convolutional Neural Network-based methods
  8. Early CNN architectures
  9. Advanced CNN architectures
  10. Alternative Methods
  11. Model-Based Deep Unrolling and Federated Methods
  12. Model-Based Deep Unrolling Networks
  13. Federated Methods
  14. Implicit Representation and Continuous Learning Networks
  15. Implicit LiDAR Network (ILN)
  16. ...and 11 more sections

Figures (1)

  • Figure 1: General pipeline of projection-based LiDAR super-resolution for autonomous driving. The process begins with a sparse 3D point cloud from a low-resolution LiDAR sensor (left), which is projected into a 2D range image representation preserving the 360-degree horizontal field of view. The low-resolution range image is then processed through a deep learning network to predict a high-resolution range image with increased vertical resolution. Finally, the enhanced range image is back-projected to 3D space, generating a dense point cloud comparable to expensive high-resolution sensors.