Data for "Semi-Automated Indoor Geometry Reconstruction for Daylight Simulation"

This repository contains the I/O data for the project <strong>"</strong>Semi-Automated Indoor Geometry Reconstruction for Daylight Simulation<strong>."</strong>Unzip the content of the zip file in the 'evaluation' sub-folder in the code repository (see references) to have the full data-code package.<br><strong>Abstract:</strong>This study presents a semi-automated pipeline for reconstructing indoor geometries from point cloud data for daylight simulation. The pipeline generates watertight models of permanent architectural surfaces with window boundaries through three steps: (1) preprocessing, (2) permanent structure reconstruction, and (3) window boundary extraction. The pipeline was evaluated in four rooms of varying complexity against manually reconstructed models, with daylight availability and glare simulations performed in <em>Radiance</em>. Daylight availability results show absolute errors below 10% for UDI, with mean TAI percentage errors within 18% for rooms with rectangular windows and up to 44% for those with non-rectangular windows. The DGP error remains under 4%, and the modelling time does not exceed 5 minutes in any scenario. The approach enables rapid generation of simulation-ready models with acceptable accuracy for CBDM.本仓库包含题为**“面向日光模拟的半自动化室内几何重建”**的项目的输入输出（I/O）数据。请将该zip压缩包的内容解压至代码仓库的'evaluation'子文件夹中（详见参考文献），以获得完整的数据-代码套件。 **摘要:** 本研究提出一套面向日光模拟的半自动化流水线，用于从点云数据（point cloud data）中重建室内几何模型。该流水线通过三个步骤生成带窗边界的永久建筑表面水密模型（watertight model）：（1）预处理阶段，（2）永久结构重建阶段，以及（3）窗边界提取阶段。 本流水线针对四间复杂度各异的房间，与手动重建模型开展了对比评估，并借助**Radiance**软件完成了日光可及性与眩光模拟实验。日光可及性的评估结果显示，UDI的绝对误差低于10%；对于带矩形窗的房间，TAI的平均百分比误差控制在18%以内，而对于带非矩形窗的房间，该误差可达44%。DGP误差始终低于4%，且所有场景下的建模耗时均不超过5分钟。本方法可快速生成满足基于气候的日光建模（CBDM，Climate-Based Daylight Modeling）精度要求的、可直接用于模拟的模型。