Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Images

2025-04-07

AI Summary

LoD3 building reconstruction faces longstanding challenges due to conflicting requirements—geographic registration, watertight geometry, façade-level semantic fidelity, and low-polygon representation—exacerbated by the intrinsic mismatch between object-oriented modeling paradigms and unstructured mesh representations. This paper introduces the first end-to-end LoD3 reconstruction framework jointly driven by street-level panoramic imagery and coarse-grained prior models: it leverages the coarse model as a reference for orthorectification, enabling texture-guided façade semantic segmentation and prior-constrained geometric optimization, while explicitly enforcing OGC LoD3 compliance. Contributions include: (1) ReLoD3—the first LoD3-specific benchmark; (2) an 11% improvement in façade segmentation accuracy; and (3) generation of lightweight, topologically sound, geographically aligned LoD3 models validated for solar potential analysis and autonomous driving simulation.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Despite recent advancements in surface reconstruction, Level of Detail (LoD) 3 building reconstruction remains an unresolved challenge. The main issue pertains to the object-oriented modelling paradigm, which requires georeferencing, watertight geometry, facade semantics, and low-poly representation -- Contrasting unstructured mesh-oriented models. In Texture2LoD3, we introduce a novel method leveraging the ubiquity of 3D building model priors and panoramic street-level images, enabling the reconstruction of LoD3 building models. We observe that prior low-detail building models can serve as valid planar targets for ortho-rectifying street-level panoramic images. Moreover, deploying segmentation on accurately textured low-level building surfaces supports maintaining essential georeferencing, watertight geometry, and low-poly representation for LoD3 reconstruction. In the absence of LoD3 validation data, we additionally introduce the ReLoD3 dataset, on which we experimentally demonstrate that our method leads to improved facade segmentation accuracy by 11% and can replace costly manual projections. We believe that Texture2LoD3 can scale the adoption of LoD3 models, opening applications in estimating building solar potential or enhancing autonomous driving simulations. The project website, code, and data are available here: https://wenzhaotang.github.io/Texture2LoD3/.

Problem

• Reconstructing LoD3 buildings with panoramic images
• Overcoming unstructured mesh model limitations
• Improving facade segmentation accuracy automatically

Innovation

• Leveraging 3D building priors and panoramic images
• Ortho-rectifying images using low-detail models
• Segmentation on textured surfaces for LoD3 reconstruction