UnderOneFacade: Worldwide Facade Semantic Segmentation Benchmark Dataset

2026-07-02

AI Summary

Existing semantic segmentation of building facades lacks a large-scale, cross-regional benchmark dataset with consistent semantics and centimeter-level annotation accuracy, hindering reliable evaluation of models’ cross-domain generalization. To address this gap, this work introduces LoFG3, the largest global 3D facade semantic segmentation benchmark to date, comprising 2.7 billion points collected across multiple countries and regions. LoFG3 employs a unified, architecture-informed hierarchical semantic labeling scheme with centimeter-level precision. Systematic evaluation of mainstream architectures—including point-based, graph-based, and Transformer models—reveals limited performance in fine-grained element recognition and cross-regional generalization, with the best model achieving only a 33% mean Intersection over Union (IoU). These results underscore the challenge posed by LoFG3 and its value as a rigorous new benchmark for advancing facade understanding.

Abstract

Globally consistent semantic digital twins require centimeter-accurate and geographically transferable 3D facade segmentation. However, progress in facade parsing is limited by the lack of large-scale, standardized benchmarks for evaluating cross-domain generalization. Existing datasets are geographically narrow, semantically inconsistent, or insufficiently precise. We introduce UnderOneFacade, the largest cross-country and cross-continent 3D facade benchmark to date, comprising centimeter-accurate point clouds with hierarchical, harmonized, and architecturally grounded semantic labels totaling 2.7 billion annotated points. Through a systematic evaluation of representative point-, graph- and transformer-based architectures, we show that current methods struggle to recognize fine-grained architectural elements and degrade significantly across geographic domains, with the best models achieving only up to 33 IoU on the fine-grained LoFG3 benchmark. By combining geometric precision with standardized semantics at unprecedented scale, UnderOneFacade establishes a rigorous benchmark for developing robust and transferable 3D segmentation models. The dataset, evaluation scripts, and pretrained models will be released upon publication.

Problem

• facade semantic segmentation
• cross-domain generalization
• 3D point clouds
• benchmark dataset
• geographic transferability

Innovation

• facade semantic segmentation
• cross-domain generalization
• centimeter-accurate point clouds
• architecturally grounded semantics
• 3D digital twins