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

TL;DR

TrueCity provides a comprehensive benchmark with synchronized real and synthetic urban point clouds, enabling analysis of domain gaps and improving 3D scene understanding models across real and simulated data.

Contribution

It introduces the first urban semantic segmentation benchmark with aligned real and synthetic data, facilitating domain gap analysis and model generalization in 3D scene understanding.

Findings

Quantifies synthetic-to-real domain shift in 3D segmentation

Highlights strategies for leveraging synthetic data to improve real-world models

Provides a new benchmark dataset for cross-domain 3D scene understanding

Abstract

3D semantic scene understanding remains a long-standing 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 segmentation-oriented domain shift analysis. We introduce TrueCity, the first urban semantic segmentation benchmark with cm-accurate 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/