HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures
This dataset addresses the need for accurate, large-scale 3D data for computer vision tasks, benefiting researchers in fields such as 3D reconstruction and AR, though it is incremental as it builds on existing data collection methods.
The authors introduced HoliCity, a city-scale 3D dataset with 6,300 high-resolution panoramas aligned to a CAD model of downtown London, achieving a median reprojection error of less than half a degree, to support research in holistic 3D structure learning and applications like reconstruction and augmented reality.
We present HoliCity, a city-scale 3D dataset with rich structural information. Currently, this dataset has 6,300 real-world panoramas of resolution $13312 \times 6656$ that are accurately aligned with the CAD model of downtown London with an area of more than 20 km$^2$, in which the median reprojection error of the alignment of an average image is less than half a degree. This dataset aims to be an all-in-one data platform for research of learning abstracted high-level holistic 3D structures that can be derived from city CAD models, e.g., corners, lines, wireframes, planes, and cuboids, with the ultimate goal of supporting real-world applications including city-scale reconstruction, localization, mapping, and augmented reality. The accurate alignment of the 3D CAD models and panoramas also benefits low-level 3D vision tasks such as surface normal estimation, as the surface normal extracted from previous LiDAR-based datasets is often noisy. We conduct experiments to demonstrate the applications of HoliCity, such as predicting surface segmentation, normal maps, depth maps, and vanishing points, as well as test the generalizability of methods trained on HoliCity and other related datasets. HoliCity is available at https://holicity.io.