ML Anthology

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng
CVPR 2020
doi:10.1109/CVPR42600.2020.00076 /cvpr/2020/chen2020cvpr-oasis/

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.

PDF CVPR Semantic Scholar

Cite

Text

Chen et al. "OASIS: A Large-Scale Dataset for Single Image 3D in the Wild." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00076

Markdown

[Chen et al. "OASIS: A Large-Scale Dataset for Single Image 3D in the Wild." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/chen2020cvpr-oasis/) doi:10.1109/CVPR42600.2020.00076

BibTeX

@inproceedings{chen2020cvpr-oasis,
  title     = {{OASIS: A Large-Scale Dataset for Single Image 3D in the Wild}},
  author    = {Chen, Weifeng and Qian, Shengyi and Fan, David and Kojima, Noriyuki and Hamilton, Max and Deng, Jia},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00076},
  url       = {https://mlanthology.org/cvpr/2020/chen2020cvpr-oasis/}
}