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):

Class-specific 3D Localization using Constellations of Object Parts

Mukta Prasad, Jan Knopp and Luc Van Gool
Proc. BMVC
Dundee, Scotland, September 2011


Improvement in acquisition systems, has resulted in the ability to capture more realistic 3D models of real world objects, creating a need for better data processing techniques, as in the case of text and images. In this paper, we address the issue of learning class-specific, deformable, 3D part-based structure for object part localization in 3D models/scenes. We employ an inference framework on fully connected part-based graphs inspired by Pictorial Structures (PS), which combine the local appearance of parts and the long-range structural properties. Using efficient tools for learning the model and performing inference, we show good results on a variety of classes, outperforming PS and Implicit Shape Models. Further, a similar inference framework is employed to find dense correspondences between 3D models, seeded by the above object part localization. Our results show promise for application in more complex 3D processing tasks such as part retrieval, pose estimation, scene understanding and recognition.

Download in pdf format
  author = {Mukta Prasad and Jan Knopp and Luc Van Gool},
  title = {Class-specific 3D Localization using Constellations of Object Parts},
  booktitle = {Proc. BMVC},
  year = {2011},
  month = {September},
  pages = {32.1--32.11},
  editor = {Jesse Hoey and Stephen McKenna and Emanuele Trucco},
  series = {BMVC 2011},
  publisher = {BMVA Press},
  keywords = {Class-specific, 3D, three-dimensional, localization, correspondence, constellation, graphical model, part based, inference, graph-based, articulated, dense}