End-to-End LiDAR optimization for 3D point cloud registration

LiDAR sensors are a key modality for 3D perception, yet they are typically designed independently of downstream tasks such as point cloud registration. Conventional registration operates on pre-acquired datasets with fixed LiDAR configurations, leading to suboptimal data collection and significant computational overhead for sampling, noise filtering, and parameter tuning. In this work, we propose an adaptive LiDAR sensing framework that dynamically adjusts sensor parameters, jointly optimizing LiDAR acquisition and registration hyperparameters. By integrating registration feedback into the sensing loop, our approach optimally balances point density, noise, and sparsity, improving registration accuracy and efficiency. Evaluations in the CARLA simulation demonstrate that our method outperforms fixed-parameter baselines while retaining generalization abilities, highlighting the potential of adaptive LiDAR for autonomous perception and robotic applications.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-02-11

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  arXiv 2602.10492
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Deep Learning Lidar Denoising Approach for Improving Atmospheric Feature Detection

  2024cited by this paper
• Deep learning-based low overlap point cloud registration for complex scenario: The review

  2024cited by this paper
• Quatro++: Robust global registration exploiting ground segmentation for loop closing in LiDAR SLAM

  2023cited by this paper
• BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

  2023cited by this paper
• LiDAR-in-the-Loop Hyperparameter Optimization

  2023influential reference
• Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance

  2023cited by this paper
• 3D Registration with Maximal Cliques

  2023cited by this paper
• Point Cloud Registration for LiDAR and Photogrammetric Data: a Critical Synthesis and Performance Analysis on Classic and Deep Learning Algorithms

  2023cited by this paper
• Adaptive weighted robust iterative closest point

  2022cited by this paper
• Deep 3D Object Detection Networks Using LiDAR Data: A Review

  2021cited by this paper
• A Benchmark for Point Clouds Registration Algorithms

  2020cited by this paper
• A Voxelized Fractal Descriptor for 3D Object Recognition

  2020cited by this paper
• Lidar for Autonomous Driving: The Principles, Challenges, and Trends for Automotive Lidar and Perception Systems

  2020cited by this paper
• Physics-based Simulation of Continuous-Wave LIDAR for Localization, Calibration and Tracking

  2019cited by this paper
• GP-ICP: Ground Plane ICP for Mobile Robots

  2019cited by this paper
• Hyperparameter optimization in black-box image processing using differentiable proxies

  2019cited by this paper
• A robust pose graph approach for city scale LiDAR mapping

  2018cited by this paper
• Open3D: A Modern Library for 3D Data Processing

  2018cited by this paper
• SLAM-driven robotic mapping and registration of 3D point clouds

  2018cited by this paper
• 3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder

  2017cited by this paper
• CARLA: An Open Urban Driving Simulator

  2017cited by this paper
• Fast Global Registration

  2016influential reference
• 3D reconstruction and multiple point cloud registration using a low precision RGB-D sensor

  2016cited by this paper
• Challenging data sets for point cloud registration algorithms

  2012cited by this paper
• Fast Point Feature Histograms (FPFH) for 3D registration

  2009cited by this paper
• Efficient variants of the ICP algorithm

  2001cited by this paper
• A Method for Registration of 3-D Shapes

  1992cited by this paper

• No citing papers are available for this paper.