Learning to reconstruct shapes from unseen classes
Name
7494-learning-to-reconstruct-shapes-from-unseen-classes.pdf
Description
Published version
Size
7.21 MB
Format
Adobe PDF
Checksum (MD5)
a5796f9981a1ccf999f5766c77445cb6
Author(s)
Zhang, Xiuming
Zhang, Zhoutong
Zhang, Chengkai
Tenenbaum, Joshua B.
Freeman, William T.
Wu, Jiajun
Date Issued
2018
Citation
Zhang, Xiuming, Zhang, Zhoutong, Zhang, Chengkai, Tenenbaum, Joshua B., Freeman, William T. et al. 2018. "Learning to reconstruct shapes from unseen classes."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. From a single image, humans are able to perceive the full 3D shape of an object by exploiting learned shape priors from everyday life. Contemporary single-image 3D reconstruction algorithms aim to solve this task in a similar fashion, but often end up with priors that are highly biased by training classes. Here we present an algorithm, Generalizable Reconstruction (GenRe), designed to capture more generic, class-agnostic shape priors. We achieve this with an inference network and training procedure that combine 2.5D representations of visible surfaces (depth and silhouette), spherical shape representations of both visible and non-visible surfaces, and 3D voxel-based representations, in a principled manner that exploits the causal structure of how 3D shapes give rise to 2D images. Experiments demonstrate that GenRe performs well on single-view shape reconstruction, and generalizes to diverse novel objects from categories not seen during training.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7494-learning-to-reconstruct-shapes-from-unseen-classes
