AdaSplats: Adaptive Splatting of Point Clouds for Accurate 3D Modeling and Real-time High-Fidelity LiDAR Simulation

TL;DR

This paper introduces AdaSplats, an adaptive splatting method for accurate 3D modeling of real-world point clouds and a fast, GPU-accelerated LiDAR simulation pipeline for autonomous vehicle testing.

Contribution

It presents a novel adaptive splat generation technique that handles variable density point clouds and a high-performance LiDAR simulator leveraging GPU parallelism.

Findings

Improved modeling of thin structures in point clouds.

Enhanced simulation speed with GPU acceleration.

Qualitative and quantitative validation against existing methods.

Abstract

LiDAR sensors provide rich 3D information about their surrounding{s} and are becoming increasingly important for autonomous vehicles tasks such as {localization}, semantic segmentation, object detection, and tracking. {Simulation} accelerates the testing, validation, and deployment of autonomous vehicles while {also} reducing cost and eliminating the risks of testing in real-world scenarios. We address the problem of high-fidelity LiDAR simulation and present a pipeline that leverages real-world point clouds acquired by mobile mapping systems. Point-based geometry representations, more specifically splats {(2D oriented disks with normals)}, have proven their ability to accurately model the underlying surface in large point clouds{, mainly with uniform density}. We introduce an adaptive splat generation method that accurately models the underlying 3D geometry {to handle real-world point clouds with variable densities}, especially for thin structures. Moreover, we introduce a {fast} LiDAR {sensor} simulator, {working} in the splatted model, {that leverages} the GPU parallel architecture with an acceleration structure while focusing on efficiently handling large point clouds. We test our LiDAR simulation in real-world conditions, showing qualitative and quantitative results compared to basic splatting and meshing techniques, demonstrating the interest of our modeling technique.