RealCity3D: A Large-scale Georeferenced
3D Shape Dataset of Real-world Cities

Congcong Wen ^{1 *}
Wenyu Han ^{1 *}
Lazarus Chok ^{1 †}
Yan Liang Tan ^{1 †}

Sheung Lung Chan ^{1 †}
Hang Zhao ²
Chen Feng ^{1 ‡}

¹New York University, ²Tsinghua University
^* Equal contributions.
^† Equal contributions.
^‡ The corresponding author is Chen Feng cfeng@nyu.edu

Abstract

Existing 3D shape datasets in the research community are generally limited to objects or scenes at the home level. City level shape datasets are rare due to the difficulty in data collection and processing. However, such datasets uniquely present a new type of 3D data with a high variance in geometric complexity and spatial layout styles, such as residential/historical/commercial buildings and skyscrapers. This work focuses on collecting such data, and proposes city generation as new tasks for data-driven content generation. Thus, we collect over 1,000,000 geo-referenced 3D building models from New York City and Zurich. We benchmark various baseline performance on two challenging tasks: (1) city layout generation, and (2) building shape generation. Moreover, we propose an auto-encoding tree neural network for 2D building footprint and 3D building cuboid generation. The dataset, tools, and algorithms will be released to the community.

Datasets

The current RealCity3D contains more than 1,000,000 geo-referenced objects of New York City and Zurich. The four different representations are provided for each object, including polygon meshes, triangle meshes, point clouds, and voxel grids.