OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
Author(s): Chen, Weifang; Qian, Shengyi; Fan, David; Kojima, Noriyuki; Hamilton, Max; et al
DownloadTo refer to this page use:
http://arks.princeton.edu/ark:/88435/pr1nz4jFull metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Chen, Weifang | - |
| dc.contributor.author | Qian, Shengyi | - |
| dc.contributor.author | Fan, David | - |
| dc.contributor.author | Kojima, Noriyuki | - |
| dc.contributor.author | Hamilton, Max | - |
| dc.contributor.author | Deng, Jia | - |
| dc.date.accessioned | 2021-10-08T19:45:51Z | - |
| dc.date.available | 2021-10-08T19:45:51Z | - |
| dc.date.issued | 2020 | en_US |
| dc.identifier.citation | Chen, Weifeng, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, and Jia Deng. "OASIS: A Large-Scale Dataset for Single Image 3D in the Wild." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020): pp. 676-685. doi:10.1109/CVPR42600.2020.00076 | en_US |
| dc.identifier.issn | 1063-6919 | - |
| dc.identifier.uri | https://openaccess.thecvf.com/content_CVPR_2020/papers/Chen_OASIS_A_Large-Scale_Dataset_for_Single_Image_3D_in_the_CVPR_2020_paper.pdf | - |
| dc.identifier.uri | http://arks.princeton.edu/ark:/88435/pr1nz4j | - |
| dc.description.abstract | 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. | en_US |
| dc.format.extent | 676 - 685 | en_US |
| dc.language.iso | en_US | en_US |
| dc.relation.ispartof | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | en_US |
| dc.rights | Author's manuscript | en_US |
| dc.title | OASIS: A Large-Scale Dataset for Single Image 3D in the Wild | en_US |
| dc.type | Conference Article | en_US |
| dc.identifier.doi | 10.1109/CVPR42600.2020.00076 | - |
| dc.identifier.eissn | 2575-7075 | - |
| pu.type.symplectic | http://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceeding | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| OasisDatasetSingleImage3DWild.pdf | 4.3 MB | Adobe PDF | View/Download |
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.