Physically Based Neural LiDAR Resimulation

2025-07-15

AI Summary

Existing NeRF methods for LiDAR simulation and large-scale scene reconstruction neglect critical sensor physics—including rolling shutter effects, time-varying laser power, and intensity attenuation—leading to geometrically and photometrically distorted synthetic point clouds. This work introduces the first neural radiance field framework explicitly incorporating a multi-scale LiDAR sensor model, featuring temporal rolling shutter modeling, range-dependent intensity attenuation, and dynamic power compensation. The resulting physically consistent LiDAR re-simulation enables novel-view synthesis with high-fidelity point cloud generation. Our method supports high-resolution scanning and enables cross-modal joint rendering of camera and LiDAR data. Quantitative evaluation across multiple real and synthetic benchmarks demonstrates significant improvements over state-of-the-art methods (e.g., 18.7% reduction in Chamfer distance); qualitative analysis further confirms enhanced geometric and radiometric fidelity. Ablation studies validate the individual contributions of each sensor-aware component. Code and datasets are publicly released.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Methods for Novel View Synthesis (NVS) have recently found traction in the field of LiDAR simulation and large-scale 3D scene reconstruction. While solutions for faster rendering or handling dynamic scenes have been proposed, LiDAR specific effects remain insufficiently addressed. By explicitly modeling sensor characteristics such as rolling shutter, laser power variations, and intensity falloff, our method achieves more accurate LiDAR simulation compared to existing techniques. We demonstrate the effectiveness of our approach through quantitative and qualitative comparisons with state-of-the-art methods, as well as ablation studies that highlight the importance of each sensor model component. Beyond that, we show that our approach exhibits advanced resimulation capabilities, such as generating high resolution LiDAR scans in the camera perspective. Our code and the resulting dataset are available at https://github.com/richardmarcus/PBNLiDAR.

Problem

• Addresses insufficient modeling of LiDAR-specific effects
• Improves accuracy in LiDAR simulation via sensor characteristics
• Enables high-resolution LiDAR scans from camera perspectives

Innovation

• Models sensor characteristics like rolling shutter
• Simulates laser power and intensity variations
• Generates high-resolution LiDAR scans