Title: Shape-from-recognition : recognition enables meta-data transfer
Authors: Thomas, Alexander ×
Ferrari, Vittorio
Leibe, Bastian
Tuytelaars, Tinne
Van Gool, Luc #
Issue Date: Dec-2009
Publisher: Academic Press
Series Title: Computer Vision and Image Understanding vol:113 issue:12 pages:1222-1234
Conference: IEEE international conference on computer vision, ICCV 2007 edition:11 location:Rio de Janeiro, Brazil date:20 October 2007
Abstract: Low-level cues in an image not only allow to infer higher-level information like the presence of an object but the inverse is also true. Category-level object recognition has now reached a level of maturity and accuracy that allows to successfully feed back its 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 different kinds of meta-data annotations for images of previously unseen object instances, in particular information on 3D shape. Meta-data can be discrete, real- or vector-valued. Our approach builds on the Implicit Shape Model of Leibe and Schiele
Object recognition [B. Leibe, A. Leonardis, B. Schiele, Robust object detection with interleaved categorization and segmentation, International Journal of Computer Vision 77 (1–3) (2008) 259–289], and extends it to transfer annotations from training images to test images. We focus on the inference of approximative 3D shape information about objects in a single 2D image. In experiments, we illustrate how our method can infer depth maps, surface normals and part labels for previously unseen object instances.
Description: Thomas A., Ferrari V., Leibe B., Tuytelaars T., Van Gool L., ''Shape-from-recognition : recognition enables meta-data transfer'', Computer vision and image understanding, vol. 113, no. 12, pp. 1222-1234, December 2009 (11th IEEE international conference on computer vision, ICCV 2007, October 14-20, 2007, Rio de Janeiro, Brazil).
ISSN: 1077-3142
Publication status: published
KU Leuven publication type: IT
Appears in Collections:ESAT - PSI, Processing Speech and Images
× corresponding author
# (joint) last author

Files in This Item:
File Description Status SizeFormat
cviu-3drr-shape_from_recognition-corr.pdfMain article Published 2145KbAdobe PDFView/Open Request a copy

These files are only available to some KU Leuven Association staff members


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science