TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding

Duc Nguyen, Yan-Ling Lai, Qilin Zhang, Prabin Gyawali, Fan Wang, Benedikt Schwab, Olaf Wysocki, Thomas H. Kolbe

Keywords: sim-to-real gap, domain adaptation, benchmark dataset, laser scanning, 3D semantic segmentation, urban point clouds, semantic 3D city models, LiDAR simulation

TL;DR: We analyze the semantic segmentation domain shift on the new TrueCity benchmark dataset with standard-harmonized urban classes, comprising real-world point clouds, their derived semantic 3D city model, and simulated point clouds of the same location.

Abstract: 3D semantic scene understanding remains a longstanding challenge in the 3D computer vision community. One of the key issues pertains to limited real-world annotated data to facilitate generalizable models. The common practice to tackle this issue is to simulate new data. Although synthetic datasets offer scalability and perfect labels, their designer-crafted scenes fail to capture real-world complexity and sensor noise, resulting in a synthetic-to-real domain gap. Moreover, no benchmark provides synchronized real and simulated point clouds for segmentationoriented domain shift analysis. We introduce TrueCity, the first urban semantic segmentation benchmark with cmaccurate annotated real-world point clouds, semantic 3D city models, and annotated simulated point clouds representing the same city. TrueCity proposes segmentation classes aligned with international 3D city modeling standards, enabling consistent evaluation of synthetic-to-real gap. Our extensive experiments on common baselines quantify domain shift and highlight strategies for exploiting synthetic data to enhance real-world 3D scene understanding. We are convinced that the TrueCity dataset will foster further development of sim-to-real gap quantification and enable generalizable data-driven models. The data, code, and 3D models are available online: https://tum-gis.github.io/TrueCity/.

Submission Number: 302