HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures

TL;DR

HoliCity is a comprehensive city-scale 3D dataset with high-resolution panoramas and accurate alignment to CAD models, enabling advanced research in 3D reconstruction, localization, and AR applications.

Contribution

The paper introduces HoliCity, a large-scale, precisely aligned 3D city dataset that supports high-level structural learning and various 3D vision tasks.

Findings

Effective for surface normal estimation and segmentation

Demonstrates generalizability of 3D vision methods

Supports city-scale reconstruction and AR applications

Abstract

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.