Looking Beyond the Visible Scene

Aditya Khosla Byoungkwon An Joseph J. Lim Antonio Torralba


Can you rank the images by their distance to the closest McDonald's? What about ranking them based on the crime rate in the area?

Answers available in the paper!


Abstract

A common thread that ties together many prior works in scene understanding is their focus on the aspects directly present in a scene such as its categorical classification or the set of objects. In this work, we propose to look beyond the visible elements of a scene; we demonstrate that a scene is not just a collection of objects and their configuration or the labels assigned to its pixels - it is so much more. From a simple observation of a scene, we can tell a lot about the environment surrounding the scene such as the potential establishments near it, the potential crime rate in the area, or even the economic climate. Here, we explore several of these aspects from both the human perception and computer vision perspective. Specifically, we show that it is possible to predict the distance of surrounding establishments such as McDonald's or hospitals even by using scenes located far from them. We go a step further to show that both humans and computers perform well at navigating the environment based only on visual cues from scenes. Lastly, we show that it is possible to predict the crime rates in an area simply by looking at a scene without any real-time criminal activity. Simply put, here, we illustrate that it is possible to look beyond the visible scene.



Paper

Looking Beyond the Visible Scene [paper] [bibtex]
Aditya Khosla*, Byoungkwon An*, Joseph J. Lim*, and Antonio Torralba
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
(* - indicates equal contribution)



Code



Supplemental Material

Coming soon!



For comments and questions, please contact Aditya Khosla.