ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding

Isaac Corley, Jonathan Lwowski, Peyman Najafirad; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 4635-4643

Abstract

A crucial part of any home is the roof over our heads to protect us from the elements. In this paper we present the Zeitview Rooftop Geometry (ZRG) dataset for residential rooftop understanding. ZRG is a large-scale residential rooftop inspection dataset of over 20k properties from across the U.S. and includes high resolution aerial orthomosaics, digital surface models (DSM), colored point clouds, and 3D roof wireframe annotations. We provide an in-depth analysis and perform several experimental baselines including roof outline extraction, monocular height estimation, and planar roof structure extraction, to illustrate a few of the numerous applications unlocked by this dataset.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Corley_2024_WACV, author = {Corley, Isaac and Lwowski, Jonathan and Najafirad, Peyman}, title = {ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4635-4643} }