一种基于神经网络隐式表达的室内建模改进方法  

An improved indoor modeling method based on neural network implicit representation

作　　者：尤桢杰 王家奎 熊伦 余子洋 YOU Zhenjie;WANG Jiakui;XIONG Lun;YU Ziyang(Hubei Key Laboratory of Optical Information and Pattern Recognition,Wuhan 430205,China;School of Optical Information and Energy Engineering,School of Mathematics and Physics,Wuhan Institute of Technology,Wuhan 430205,China;Wuhan Veily Technology Co.,Ltd,Wuhan 430200,China)

机构地区：[1]光学信息与模式识别湖北省重点实验室,湖北武汉430205 [2]武汉工程大学光电信息与能源工程学院、数理学院,湖北武汉430205 [3]武汉唯理科技有限公司,湖北武汉430200

出　　处：《武汉工程大学学报》2025年第2期202-209,共8页Journal of Wuhan Institute of Technology

基　　金：国家自然科学基金(91963207)。

摘　　要：本文提出一种基于神经网络隐式表达的室内三维重建改进方法,旨在解决仅使用彩色图像进行室内重建时效果不佳的问题。具体步骤包括:通过经典三维重建软件COLMAP获取相机参数和稀疏点云,利用线性特征的映射与定位工具箱LIMAP获取三维线段模型;通过深度估计和法向量估计获取深度信息和法向量信息;最终将深度信息、法向量信息和稀疏点云作为先验信息输入神经辐射场,以提高重建精度。在Scannet公开数据集上的实验结果显示,引入先验信息显著提升了重建效果,F分数达到0.70,峰值信噪比约为24 dB。在Scannet公开数据集和自建数据集上的实验结果表明,该方法有效解决了弱纹理区域的重建缺陷,显著提升了细节重建效果,对虚拟现实和数字建筑应用具有重要意义。This paper proposes an improved indoor 3D reconstruction method based on neural network implicit representation,aiming to solve the problem of poor reconstruction effect when only using color images for indoor reconstruction.The specific steps include:obtaining camera parameters and sparse point clouds through the classic 3D reconstruction software COLMAP,and using the Linear Feature Mapping and Localization Toolbox LIMAP to obtain a 3D line segment model;obtaining depth information and normal vector information through depth estimation and normal vector estimation;finally,inputting depth information,normal vector information,and sparse point clouds as prior information into the neural radiance field to improve the reconstruction accuracy.Experimental results on the Scannet public dataset showed that introducing prior information significantly improves the reconstruction effect,with an F-score of 0.70 and a peak signal-to-noise ratio of approximately 24 dB.The experimental results on the Scannet public dataset and the self-built dataset demonstrate that this method effectively solves the reconstruction defect in weak-texture areas,significantly improving the detail reconstruction effect,hence has substantial promise for applications in virtual reality and digital architecture.

关 键 词：神经辐射场 隐式表达 深度估计 法向量估计 符号距离场 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]