2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
Alexei A. Efros , Robotics Institute, Carnegie Mellon University, USA
Martial Hebert , Robotics Institute, Carnegie Mellon University, USA
Santosh K. Divvala , Robotics Institute, Carnegie Mellon University, USA
We describe a preliminary investigation of utilising large amounts of unlabelled image data to help in the estimation of rough scene layout. We take the single-view geometry estimation system of Hoiem et al  as the baseline and see if it is possible to improve its performance by considering a set of similar scenes gathered from the web. The two complimentary approaches being considered are 1) improving surface classification by using average geometry estimated from the matches, and 2) improving surface segmentation by injecting segments generated from the average of the matched images. The system is evaluated using the labelled 300-image dataset of Hoiem et al. and shows promising results.
Alexei A. Efros, Martial Hebert, Santosh K. Divvala, "Can similar scenes help surface layout estimation?", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-8, 2008, doi:10.1109/CVPRW.2008.4562951