This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Shape-from-Recognition: Recognition enables Meta-data Transfer

A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, L. Van Gool
Computer Vision and Image Understanding
Vol. 113, No. 12, pp. 1222-1234, December 2009


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 metadata 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 (2008), 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.

Download in pdf format
  author = {A. Thomas and V. Ferrari and B. Leibe and T. Tuytelaars and L. Van Gool},
  title = {Shape-from-Recognition: Recognition enables Meta-data Transfer},
  journal = {Computer Vision and Image Understanding},
  year = {2009},
  month = {December},
  pages = {1222-1234},
  volume = {113},
  number = {12},
  keywords = {object class detection; depth estimation; meta-data transfer}