iVISION-2DCD: A Long-Term Change Detection Dataset for Large-Scale Outdoor Construction Monitoring

2026-07-03

AI Summary

This work addresses the limitations of existing 2D change detection methods in large-scale outdoor construction scenarios, which stem from the absence of publicly available datasets supporting arbitrary viewpoints. To bridge this gap, we introduce iVISION-2DCD, the first viewpoint-robust 2D change detection benchmark tailored for construction environments. Leveraging high-density LiDAR point clouds, our framework synthesizes photorealistic multi-temporal, multi-view images through view synthesis and physically based rendering, accompanied by precise change annotations. We further devise a semi-automatic semantic segmentation pipeline that preserves real-world complexity while resolving challenges in bi-temporal alignment and viewpoint diversity. This dataset establishes a new benchmark that poses significant challenges for current algorithms and offers a valuable platform for advancing research in construction automation, computer vision, and robotics.

Abstract

Automation in construction is essential for reducing costs and human errors in large-scale projects. We approach the construction progress monitoring from the aspect of detecting changes in construction sites. As construction buildings continue to evolve in geometry and appearance over time, change detection need to be performed from arbitrary camera viewpoints. This necessitates developing 2D Change Detection (2DCD) algorithms that operate robustly across diverse camera perspectives at construction sites. While developing and evaluating such systems is data-intensive, no open-source benchmark dataset exists at the intersection of 2D change detection and construction automation research. Data collection using Unmanned Aerial Vehicles (UAVs) is gaining its popularity in outdoor large-scale surveying. However, in active construction sites conducting drone missions equipped with high-end sensors imposes safety concerns. Flight trajectory and collected camera viewpoints can be significantly limited. To address this critical gap, we introduce iVISION-2DCD, a large-scale synthetically generated dataset from dense LiDAR point clouds with photorealistic input images and accurate ground truth annotations. Our dataset formally defines the problem of viewpoint-robust 2DCD at construction sites and captures the inherent complexities of real-world deployment. In this paper, we present our systematic methodology for synthetic data generation, developing novel view synthesis techniques to overcome bi-temporal alignment and viewpoint diversity challenges, and implementing semi-automated semantic segmentation with change label generation while preserving challenging real-world cases. Benchmark evaluations using state-of-the-art 2DCD algorithms demonstrate that iVISION-2DCD poses novel research challenges for the computer vision and robotics communities.

Problem

• 2D Change Detection
• Construction Monitoring
• Viewpoint Robustness
• Benchmark Dataset
• Outdoor Construction

Innovation

• 2D Change Detection
• synthetic dataset
• view synthesis
• construction monitoring
• LiDAR-based rendering