Scholarlink

Abstract <p>The rapid reconstruction of partially destroyed cultural heritage objects is crucial in architectural history. Many significant structures have suffered damage from erosion, earthquakes, or human activity, often leaving only the armature intact. Simplified 3D reconstruction techniques using digital cameras and laser rangefinders are essential for these monuments, frequently located in abandoned areas. However, interior surfaces visible through exterior openings complicate reconstruction by introducing outliers in the 3D point cloud. This paper introduces the <Emphasis FontCategory="NonProportional">WireNetV3</Emphasis> model for precise 3D segmentation of wire structures in color images. The model distinguishes between front and interior surfaces, filtering outliers during feature matching. Building on SegFormer 3D and <Emphasis FontCategory="NonProportional">WireNetV2</Emphasis>, our approach integrates transformers with task-specific features and introduces a novel loss function, WireSDF, for distance calculation from wire axes. Evaluations on datasets featuring the Shukhov Tower and a church dome demonstrate that <Emphasis FontCategory="NonProportional">WireNetV3</Emphasis> surpasses existing methods in Intersection-over-Union metrics and 3D model accuracy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Wire-Structured Object 3D Point Cloud Filtering Using a Transformer Model

  • 期刊论文

  • 发表日期：

    2025年12月19日

查看全文
  • V. Kniaz,
  • V. Knyaz,
  • T. Skrypitsyna,
  • P. Moshkantsev,
  • A. Bordodymov

摘要

Abstract

The rapid reconstruction of partially destroyed cultural heritage objects is crucial in architectural history. Many significant structures have suffered damage from erosion, earthquakes, or human activity, often leaving only the armature intact. Simplified 3D reconstruction techniques using digital cameras and laser rangefinders are essential for these monuments, frequently located in abandoned areas. However, interior surfaces visible through exterior openings complicate reconstruction by introducing outliers in the 3D point cloud. This paper introduces the WireNetV3 model for precise 3D segmentation of wire structures in color images. The model distinguishes between front and interior surfaces, filtering outliers during feature matching. Building on SegFormer 3D and WireNetV2, our approach integrates transformers with task-specific features and introduces a novel loss function, WireSDF, for distance calculation from wire axes. Evaluations on datasets featuring the Shukhov Tower and a church dome demonstrate that WireNetV3 surpasses existing methods in Intersection-over-Union metrics and 3D model accuracy.