OASIS: A Large-Scale Dataset for Single Image 3D in the Wild - Crossminds
CrossMind.ai logo

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

Sep 29, 2020
|
33 views
|
Details
Authors: Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng Description: 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.

Comments
loading...
Reactions (0) | Note
    📝 No reactions yet
    Be the first one to share your thoughts!
loading...
Recommended