Enhancing 3D point accuracy of laser scanner through multi-stage convolutional neural network for applications in construction

TL;DR

This paper introduces a multi-stage neural network approach to significantly improve the 3D point accuracy of laser scanners in indoor environments, enabling low-end devices to achieve high-precision measurements.

Contribution

The paper presents a novel correction framework combining geometric processing with neural network refinement to reduce systematic errors in laser scanner data.

Findings

MSE reduced by over 70%

PSNR increased by about 6 dB

Low-end scanners approach high-end accuracy

Abstract

We propose a multi-stage convolutional neural network (MSCNN) based integrated method for reducing uncertainty of 3D point accuracy of lasar scanner (LS) in rough indoor rooms, providing more accurate spatial measurements for high-precision geometric model creation and renovation. Due to different equipment limitations and environmental factors, high-end and low-end LS have positional errors. Our approach pairs high-accuracy scanners (HAS) as references with corresponding low-accuracy scanners (LAS) of measurements in identical environments to quantify specific error patterns. By establishing a statistical relationship between measurement discrepancies and their spatial distribution, we develop a correction framework that combines traditional geometric processing with targeted neural network refinement. This method transforms the quantification of systematic errors into a supervised learning problem, allowing precise correction while preserving critical geometric features. Experimental results in our rough indoor rooms dataset show significant improvements in measurement accuracy, with mean square error (MSE) reductions exceeding 70% and peak signal-to-noise ratio (PSNR) improvements of approximately 6 decibels. This approach enables low-end devices to achieve measurement uncertainty levels approaching those of high-end devices without hardware modifications.