# Texture2LoD3: Enabling LoD3 Building Reconstruction With Panoramic Images

arXiv: https://arxiv.org/abs/2504.05249 · HTML: https://mlsanity.com/paper/2504.05249/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 64 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks](https://mlsanity.com/paper/2305.06314/) (2023)
- [DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds](https://mlsanity.com/paper/2106.00376/) (2021)
- [ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset](https://mlsanity.com/paper/2411.04865/) (2024)
- [WinSyn: A High Resolution Testbed for Synthetic Data](https://mlsanity.com/paper/2310.08471/) (2023)
- [Classifying point clouds at the facade-level using geometric features and deep learning networks](https://mlsanity.com/paper/2402.06506/) (2024)

## Built on by (most cited first, 7 of 7)

- [CM2LoD3: Reconstructing LoD3 Building Models Using Semantic Conflict Maps](https://mlsanity.com/paper/2508.15672/) (2025)
- [TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding](https://mlsanity.com/paper/2511.07007/) (2025)
- [RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning](https://mlsanity.com/paper/2504.12167/) (2025)
- [SVI2LoD3: Agent-Driven Reconstruction of LoD3 Facade Openings in Semantic 3D City Models from Volunteered Street View Imagery using Large Language and Visual Models](https://mlsanity.com/paper/2608.29992/) (2026)
- [GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors](https://mlsanity.com/paper/2604.11401/) (2026)
- [KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling](https://mlsanity.com/paper/2609.07298/) (2026)
- [ProxyBuild: Text-Guided Structured 3D Building Generation with Mesh-Anchored Procedural Proxies](https://mlsanity.com/paper/2609.23386/) (2026)

## Abstract (arXiv)

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/.