TY - CONF
T1 - CUMULATIVE ASSESSMENT FOR URBAN 3D MODELING
AU - Hagstrom, Shea
AU - Pak, Hee Won
AU - Ku, Stephanie
AU - Wang, Sean
AU - Hager, Gregory
AU - Brown, Myron
N1 - Funding Information:
We thank the authors of [4] and [12] for their assistance and advice in facilitating our extension of their open source works. This work was supported by the Intelligence Advanced Research Projects Activity (IARPA) contract no. 2017-17032700004. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA or the U.S. Government.
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Urban 3D modeling from satellite images requires accurate semantic segmentation to delineate urban features, multiple view stereo for 3D reconstruction of surface heights, and 3D model fitting to produce compact models with accurate surface slopes. In this work, we present a cumulative assessment metric that succinctly captures error contributions from each of these components. We demonstrate our approach by providing challenging public datasets and extending two open source projects to provide an end-to-end 3D modeling baseline solution to stimulate further research and evaluation with a public leaderboard.
AB - Urban 3D modeling from satellite images requires accurate semantic segmentation to delineate urban features, multiple view stereo for 3D reconstruction of surface heights, and 3D model fitting to produce compact models with accurate surface slopes. In this work, we present a cumulative assessment metric that succinctly captures error contributions from each of these components. We demonstrate our approach by providing challenging public datasets and extending two open source projects to provide an end-to-end 3D modeling baseline solution to stimulate further research and evaluation with a public leaderboard.
KW - Benchmarks
KW - Metrics
KW - Multiple view stereo
KW - Semantic segmentation
KW - Urban 3D modeling
UR - http://www.scopus.com/inward/record.url?scp=85129840691&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129840691&partnerID=8YFLogxK
U2 - 10.1109/IGARSS47720.2021.9554754
DO - 10.1109/IGARSS47720.2021.9554754
M3 - Paper
AN - SCOPUS:85129840691
SP - 3261
EP - 3264
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -