Learning Shape Priors for Single-View 3D Completion And Reconstruction
Name
1809.05068.pdf
Description
Accepted version
Size
7.74 MB
Format
Unknown
Checksum (MD5)
e5984db920e610a7ba5fbf0e26756e0d
Author(s)
Wu, Jiajun
Zhang, Chengkai
Zhang, Xiuming
Zhang, Zhoutong
Freeman, William T.
Tenenbaum, Joshua B.
Date Issued
October 2018
Journal
European Conference on Computer Vision
Publisher
Springer International Publishing
Citation
Wu, Jiajun, Zhang, Chengkai, Zhang, Xiuming, Zhang, Zhoutong, Freeman, William T. et al. 2018. "Learning Shape Priors for Single-View 3D Completion And Reconstruction."
Version
Author's final manuscript
Abstract
© 2018, Springer Nature Switzerland AG. The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks. In fact, there is another level of ambiguity that is often overlooked: among plausible shapes, there are still multiple shapes that fit the 2D image equally well; i.e., the ground truth shape is non-deterministic given a single-view input. Existing fully supervised approaches fail to address this issue, and often produce blurry mean shapes with smooth surfaces but no fine details. In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors. The learned priors serve as a regularizer, penalizing the model only if its output is unrealistic, not if it deviates from the ground truth. Our design thus overcomes both levels of ambiguity aforementioned. Experiments demonstrate that ShapeHD outperforms state of the art by a large margin in both shape completion and shape reconstruction on multiple real datasets.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-01252-6_40
