Supporting data for "CIM-WV: A 2D semantic segmentation dataset of rich window view contents in high-rise, high-density Hong Kong based on photorealistic City Information Models"

<p dir="ltr">This is the official repository of the CIM-WV dataset. For technical details, please refer to:</p><p dir="ltr">Li, M., Yeh, A. G. & Xue, F. (2023). CIM-WV: A 2D semantic segmentation dataset of rich window view contents in high-rise, high-density Hong Kong based on photorealistic City Information Models. Urban Informatics, 1-24.</p><p dir="ltr">This study was supported in part by the Department of Science and Technology of Guangdong Province (GDST) (2020B1212030009, 2023A1515010757) and the University of Hong Kong (203720465).</p><p dir="ltr"><b>Overview of CIM-WV</b></p><p dir="ltr">This paper presents a City Information Model (CIM)-generated Window View (CIM-WV) dataset comprising 2,000 annotated images collected in the high-rise, high-density urban areas of Hong Kong. </p><p dir="ltr">1) Window view images of CIM-WV depict diversified urban scenes of Hong Kong at different locations, elevations, and orientations</p><p dir="ltr">2) The CIM-WV includes seven semantic labels, i.e., building, sky, vegetation, road, waterbody, vehicle, and terrain.</p><p dir="ltr">In addition, we provide variants of DeepLab V3+ models trained on CIM-WV, real window view images, Google Earth CIM-generated window view images from New York, and Google Earth CIM-generated window view images from Singapore, respectively.</p><p dir="ltr">You can modify the source code <a href="https://github.com/LuZaiJiaoXiaL/pytorch-deeplabv3plus_CIMWV" rel="noreferrer" target="_blank">here</a> to use the trained DeepLab V3+ models. </p><p dir="ltr"><b>Contribution</b></p><p dir="ltr">1) CIM-WV is the first public CIM-generated photorealistic window view dataset with rich semantics. </p><p dir="ltr">2) Comparative analysis shows a more accurate window view assessment using deep learning from CIM-WV than deep transfer learning from ground-level views.</p><p dir="ltr">3) For urban researchers and practitioners, our publicly accessible deep learning models trained on CIM-WV enable novel multi-source window view-based urban applications including precise real estate valuation, improvement of built environment, and window view-related urban analytics.</p><p dir="ltr">Please cite our paper and dataset, if you find our work useful for your research and practices. Many thanks.</p><p dir="ltr">For any inquiries, please feel free to contact Maosu at maosulee@connect.hku.hk or Dr. Frank at xuef@hku.hk.</p>