TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding
This addresses the problem of domain shift in 3D computer vision for researchers, providing a new benchmark for segmentation-oriented analysis, though it is incremental as it builds on existing simulation practices.
The paper tackles the challenge of limited real-world annotated data for 3D semantic scene understanding by introducing TrueCity, a benchmark with cm-accurate annotated real and simulated point clouds for the same city, which quantifies the synthetic-to-real domain gap and shows strategies to enhance real-world understanding.
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/