This paper presents a framework to address the challenges involved in
building point cloud cleaning, plane detection, and semantic segmentation, with
the ultimate goal of enhancing building modeling. We focus in the cleaning
stage on removing outliers from the acquired point cloud data by employing an
adaptive threshold technique based on z-score measure. Following the cleaning
process, we perform plane detection using the robust RANSAC paradigm. The goal
is to carry out multiple plane segmentations, and to classify segments into
distinct categories, such as floors, ceilings, and walls. The resulting
segments can generate accurate and detailed point clouds representing the
building's architectural elements. Moreover, we address the problem of semantic
segmentation, which plays a vital role in the identification and classification
of different components within the building, such as walls, windows, doors,
roofs, and objects. Inspired by the PointNet architecture, we propose a deep
learning architecture for efficient semantic segmentation in buildings. The
results demonstrate the effectiveness of the proposed framework in handling
building modeling tasks, paving the way for improved accuracy and efficiency in
the field of building modelization.

提出了一个用于建筑模型的框架，针对点云清理、平面检测和语义分割等挑战进行处理，通过自适应阈值技术来清除异常值，并采用稳健的 RANSAC 算法进行平面检测和基于 PointNet 架构的深度学习方法进行建筑物的语义分割，结果表明该框架在建筑模型任务中具有高效和准确性，为建筑模型领域的提高准确性和效率铺平了道路。

构建点云清洗、平面检测和语义分割的框架

A Framework for Building Point Cloud Cleaning, Plane Detection and  Semantic Segmentation

This paper presents a neural network built upon Transformers, namely PlaneTR,
to simultaneously detect and reconstruct planes from a single image. Different
from previous methods, PlaneTR jointly leverages the context information and
the geometric structures in a sequence-to-sequence way to holistically detect
plane instances in one forward pass. Specifically, we represent the geometric
structures as line segments and conduct the network with three main components:
(i) context and line segments encoders, (ii) a structure-guided plane decoder,
(iii) a pixel-wise plane embedding decoder. Given an image and its detected
line segments, PlaneTR generates the context and line segment sequences via two
specially designed encoders and then feeds them into a Transformers-based
decoder to directly predict a sequence of plane instances by simultaneously
considering the context and global structure cues. Finally, the pixel-wise
embeddings are computed to assign each pixel to one predicted plane instance
which is nearest to it in embedding space. Comprehensive experiments
demonstrate that PlaneTR achieves a state-of-the-art performance on the ScanNet
and NYUv2 datasets.

使用基于 Transformers 的神经网络 PlaneTR 从单个图像中同时检测和重构平面。