Transient attributes for high-level understanding and editing of outdoor scenes

Abstract

We live in a dynamic visual world where the appearance of scenes changes dramatically from hour to hour or season to season. In this work we study "transient scene attributes" -- high level properties which affect scene appearance, such as "snow", "autumn", "dusk", "fog". We define 40 transient attributes and use crowdsourcing to annotate thousands of images from 101 webcams. We use this "transient attribute database" to train regressors that can predict the presence of attributes in novel images. We demonstrate a photo organization method based on predicted attributes. Finally we propose a high-level image editing method which allows a user to adjust the attributes of a scene, e.g. change a scene to be "snowy" or "sunset". To support attribute manipulation we introduce a novel appearance transfer technique which is simple and fast yet competitive with the state-of-the-art. We show that we can convincingly modify many transient attributes in outdoor scenes.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jul 27, 2014
Source ID
10.1145/2601097.2601101

Entities

People

  • Chao Qian
  • James Hays
  • Pierre-yves Laffont
  • Xiaofeng Tao
  • Zhile Ren

Organizations

  • Air Force Research Laboratory
  • Brown University
  • National Science Foundation

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computer Vision.
  • Database Systems and Applications