SIP: Site in Pieces- A Dataset of Disaggregated Construction-Phase 3D Scans for Semantic Segmentation and Scene Understanding

TL;DR

SIP is a novel dataset of real-world, fragmented 3D LiDAR scans from construction sites, designed to improve semantic segmentation and scene understanding in practical, cluttered environments.

Contribution

The paper introduces SIP, a construction-specific 3D LiDAR dataset capturing realistic, fragmented scenes with detailed annotations, addressing limitations of existing datasets.

Findings

Provides a challenging benchmark for segmentation algorithms

Includes diverse construction-related objects and environments

Facilitates development of robust 3D perception methods for construction sites

Abstract

Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development. LiDAR is widely used in construction because it offers advantages over camera-based systems, performing reliably in cluttered and dynamically changing conditions. Yet most public datasets for 3D perception are derived from densely fused scans with uniform sampling and complete visibility, conditions that do not reflect real construction sites. Field data are often collected as isolated single-station LiDAR views, constrained by safety requirements, limited access, and ongoing operations. These factors lead to radial density decay, fragmented geometry, and view-dependent visibility-characteristics that remain underrepresented in existing datasets. This paper presents SIP, Site in Pieces, a dataset created to reflect the practical constraints of LiDAR acquisition during construction. SIP provides indoor and outdoor scenes captured with a terrestrial LiDAR scanner and annotated at the point level using a taxonomy tailored to construction environments: A. Built Environment, B. Construction Operations, and C. Site Surroundings. The dataset includes both structural components and slender temporary objects such as scaffolding, MEP piping, and scissor lifts, where sparsity caused by occlusion and fragmented geometry make segmentation particularly challenging. The scanning protocol, annotation workflow, and quality control procedures establish a consistent foundation for the dataset. SIP is openly available with a supporting Git repository, offering adaptable class configurations that streamline adoption within modern 3D deep learning frameworks. By providing field data that retain real-world sensing characteristics, SIP enables robust benchmarking and contributes to advancing construction-oriented 3D vision tasks.