ZAHA: Introducing the Level of Facade Generalization and the Large-Scale Point Cloud Facade Semantic Segmentation Benchmark Dataset

MCML Authors

Yan Xia

Dr.

* Former Member

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Magdalena Wysocki

→ Group Nassir Navab
 Computer Aided Medical Procedures & Augmented Reality

Daniel Cremers

Prof. Dr.

Director

Computer Vision & Artificial Intelligence

Abstract

Facade semantic segmentation is a long-standing challenge in photogrammetry and computer vision. Although the last decades have witnessed the influx of facade segmentation methods, there is a lack of comprehensive facade classes and data covering the architectural variability. In ZAHA11Project page: https://github.com/OloOcki/zaha, we introduce Level of Facade Generalization (LoFG), novel hierarchical facade classes designed based on international urban modeling standards, ensuring compatibility with real-world challenging classes and uniform methods' comparison. Realizing the LoFG, we present to date the largest semantic 3D facade segmentation dataset, providing 601 million annotated points at five and 15 classes of LoFG2 and LoFG3, respectively. More-over, we analyze the performance of baseline semantic segmentation methods on our introduced LoFG classes and data, complementing it with a discussion on the unresolved challenges for facade segmentation. We firmly believe that ZAHA shall facilitate further development of 3D facade semantic segmentation methods, enabling robust segmentation indispensable in creating urban digital twins.

inproceedings

---

WACV 2025

IEEE/CVF Winter Conference on Applications of Computer Vision. Tucson, AZ, USA, Feb 28-Mar 04, 2025.

---

Authors

O. Wysocki • Y. Tan • T. Froech • Y. Xia • M. Wysocki • L. Hoegner • D. Cremers • C. Holst

---

Links

DOI GitHub

---

Research Areas

 B1 | Computer Vision

 C1 | Medicine