Shape-from-recognition: Recognition Enables Meta-data Transfer

Alexander Thomas, Vittorio Ferrari, Bastian Leibe, Tinne Tuytelaars, Luc Van Gool

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

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 [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.
Original languageEnglish
Pages (from-to)1222-1234
Number of pages13
JournalComputer Vision and Image Understanding
Issue number12
Publication statusPublished - 1 Dec 2009

Keywords / Materials (for Non-textual outputs)

  • Computer vision, Object recognition, Shape-from-X


Dive into the research topics of 'Shape-from-recognition: Recognition Enables Meta-data Transfer'. Together they form a unique fingerprint.

Cite this