TY - GEN
T1 - SAIL-VOS 3D
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
AU - Hu, Yuan Ting
AU - Wang, Jiahong
AU - Yeh, Raymond A.
AU - Schwing, Alexander G.
N1 - Funding Information:
7. Conclusion We introduce SAIL-VOS 3D and develop a baseline for 3D mesh reconstruction from video data. In a first study we observe temporal data to aid reconstruction. We hope SAIL-VOS 3D facilitates further research in this direction. Acknowledgements: This work is supported in part by NSF under Grant #1718221, 2008387, 2045586, MRI #1725729, and NIFA award 2020-67021-32799, UIUC, Samsung, Amazon, 3M, and Cisco Systems Inc. (Gift Award CG 1377144 - thanks for access to Arcetri).
Publisher Copyright:
© 2021 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - Extracting detailed 3D information of objects from video data is an important goal for holistic scene understanding. While recent methods have shown impressive results when reconstructing meshes of objects from a single image, results often remain ambiguous as part of the object is unobserved. Moreover, existing image-based datasets for mesh reconstruction don't permit to study models which integrate temporal information. To alleviate both concerns we present SAIL-VOS 3D: a synthetic video dataset with frame-by-frame mesh annotations which extends SAIL-VOS. We also develop first baselines for reconstruction of 3D meshes from video data via temporal models. We demonstrate efficacy of the proposed baseline on SAIL-VOS 3D and Pix3D, showing that temporal information improves reconstruction quality. Resources and additional information are available at http://sailvos.web.illinois.edu.
AB - Extracting detailed 3D information of objects from video data is an important goal for holistic scene understanding. While recent methods have shown impressive results when reconstructing meshes of objects from a single image, results often remain ambiguous as part of the object is unobserved. Moreover, existing image-based datasets for mesh reconstruction don't permit to study models which integrate temporal information. To alleviate both concerns we present SAIL-VOS 3D: a synthetic video dataset with frame-by-frame mesh annotations which extends SAIL-VOS. We also develop first baselines for reconstruction of 3D meshes from video data via temporal models. We demonstrate efficacy of the proposed baseline on SAIL-VOS 3D and Pix3D, showing that temporal information improves reconstruction quality. Resources and additional information are available at http://sailvos.web.illinois.edu.
UR - http://www.scopus.com/inward/record.url?scp=85116073452&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116073452&partnerID=8YFLogxK
U2 - 10.1109/CVPRW53098.2021.00375
DO - 10.1109/CVPRW53098.2021.00375
M3 - Conference contribution
AN - SCOPUS:85116073452
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 3359
EP - 3369
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
PB - IEEE Computer Society
Y2 - 19 June 2021 through 25 June 2021
ER -