TY - GEN
T1 - Planar Surface Reconstruction from Sparse Views
AU - Jin, Linyi
AU - Qian, Shengyi
AU - Owens, Andrew
AU - Fouhey, David F.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses. While prior approaches have successfully created object-centric reconstructions of many scenes, they fail to exploit other structures, such as planes, which are typically the dominant components of indoor scenes. In this paper, we reconstruct planar surfaces from multiple views, while jointly estimating camera pose. Our experiments demonstrate that our method is able to advance the state of the art of reconstruction from sparse views, on challenging scenes from Matterport3D.
AB - The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses. While prior approaches have successfully created object-centric reconstructions of many scenes, they fail to exploit other structures, such as planes, which are typically the dominant components of indoor scenes. In this paper, we reconstruct planar surfaces from multiple views, while jointly estimating camera pose. Our experiments demonstrate that our method is able to advance the state of the art of reconstruction from sparse views, on challenging scenes from Matterport3D.
UR - http://www.scopus.com/inward/record.url?scp=85120988876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85120988876&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.01275
DO - 10.1109/ICCV48922.2021.01275
M3 - Conference contribution
AN - SCOPUS:85120988876
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 12971
EP - 12980
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -