SUN360 Panorama Database

Introduction:

The goal of the SUN360 panorama database is to provide academic researchers in computer vision, computer graphics and computational photography, cognition and neuroscience, human perception, machine learning and data mining, with a comprehensive collection of annotated panoramas covering 360x180-degree full view for a large variety of environmental scenes, places and the objects within. To build the core of the dataset, we download a huge number of high-resolution panorama images from the Internet, and group them into different place categories. Then, we designed a WebGL annotation tool for annotating the polygons and cuboids for objects in the scene.

Browsers:

You need a WebGL enable browser to view the annotation interface in 3D.

Tested Browsers:

Works with the latest versions of Chrome, Firefox, Safari and Opera on Mac.

For Safari, open the Safari menu and select Preferences. Click the Advanced tab in the Preferences window. At the bottom of the window, check the Show Develop menu in menu bar checkbox. Then, open the Develop menu in the menu bar and select Enable WebGL.

Citation:

J. Xiao, K. A. Ehinger, A. Oliva and A. Torralba. Recognizing Scene Viewpoint using Panoramic Place Representation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR2012)

Before Annotation:

Sign up here and log in using your account before starting annotation!

Download SUN360 Dataset:

To download the panoramas at various resolutions (we have up to 9104x4552 resolution), please email Jianxiong Xiao.