Back

OASIS

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

OASIS

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.

View this Dataset
->
University of Michigan,Ann Arbor
View author website
Task
3D Reconstruction / Photogrammetry
Annotation Types
3D Point Cloud
102000
Items
4
Classes
140000
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
Research Only