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

Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 679-688

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2020_CVPR,
author = {Chen, Weifeng and Qian, Shengyi and Fan, David and Kojima, Noriyuki and Hamilton, Max and Deng, Jia},
title = {OASIS: A Large-Scale Dataset for Single Image 3D in the Wild},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}