Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

Authors:

1 January 2007

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

No. 15505499,p. 1-8
DOI:10.1109/iccv.2007.4408831

Abstract

Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer meta-data such as depth cues, 3D points, or object decomposition in images of previously unseen object instances. Our approach builds on the implicit shape model of Leibe and Schiele, and extends it to transfer annotations from training images to test images. Experimental results validate the viability of our approach.

Keywords

This publication has 9 references indexed in Scilit:

Single View Reconstruction of Curved Surfaces
2006
Putting Objects in Perspective
2006
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
2006
A performance evaluation of local descriptors
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
Pedestrian Detection in Crowded Scenes
2005
Geometric context from a single image
2005
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision, 2004
Interleaved Object Categorization and Segmentation
2003
Image analogies
2001