TY - JOUR
T1 - OASis
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
AU - Chen, Weifeng
AU - Qian, Shengyi
AU - Fan, David
AU - Kojima, Noriyuki
AU - Hamilton, Max
AU - Deng, Jia
N1 - Funding Information:
We have presented OASIS, a dataset of rich human 3D annotations. We trained and evaluated leading models on a variety of single-image tasks. We expect OASIS to be a useful resource for 3D vision research. Acknowledgement This work was partially supported by a National Science Foundation grant (No. 1617767), a Google gift, and a Princeton SEAS innovation grant.
Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image. We hypothesize that a major obstacle to single-image 3D is data. We address this issue by presenting Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of annotations of detailed 3D geometry for 140,000 images. We train and evaluate leading models on a variety of single-image 3D tasks. We expect OASIS to be a useful resource for 3D vision research. Project site: https://pvl.cs.princeton.edu/OASIS.
AB - Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image. We hypothesize that a major obstacle to single-image 3D is data. We address this issue by presenting Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of annotations of detailed 3D geometry for 140,000 images. We train and evaluate leading models on a variety of single-image 3D tasks. We expect OASIS to be a useful resource for 3D vision research. Project site: https://pvl.cs.princeton.edu/OASIS.
UR - http://www.scopus.com/inward/record.url?scp=85094677202&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094677202&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.00076
DO - 10.1109/CVPR42600.2020.00076
M3 - Conference article
AN - SCOPUS:85094677202
SN - 1063-6919
SP - 676
EP - 685
JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
M1 - 9157390
Y2 - 14 June 2020 through 19 June 2020
ER -