← Back to papers
2020 CVPR CVPR 2020

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

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.

🌉 Interdisciplinary Bridge — Computer Vision and Deep Learning and Machine Learning
🧭 Keyword Pioneer — single-image 3d
🐣 Hot Topic Early Bird — 3d geometry
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Weifeng Chen , Shengyi Qian , David Fan , Noriyuki Kojima , Max Hamilton , Jia Deng

Topics

Machine Learning > Core Methods > Regression Deep Learning > Techniques > Pretraining Computer Vision > Analysis > 3D Vision Computer Vision > Domain-Specific > Autonomous Driving Computer Vision > Processing > Depth Estimation

Keywords

3d reconstruction depth estimation surface normal estimation geometric reasoning surface normal 3d geometry single-image 3d single-view 3d
Download PDF

Related papers

Deep Polarization Cues for Transparent Object Segmentation 2020
HRank: Filter Pruning Using High-Rank Feature Map 2020
Panoptic-Based Image Synthesis 2020
Select, Supplement and Focus for RGB-D Saliency Detection 2020
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings 2020