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):

Scene Cut: Class-specific Object Detection and Segmentation in 3D Scenes

Jan Knopp, Mukta Prasad and Luc Van Gool
Hanghzou, China, May 2011


In this paper we present a method to combine the detection and segmentation of object categories from 3D scenes. In the process, we combine the top-down cues available from object detection technique of Implicit Shape Models and the bottom-up power of Markov Random Fields for the purpose of segmentation. While such approaches have been tried for the 2D image problem domain before, this is the first application of such a method in 3D. 3D scene understanding is prone to many problems different from 2D owing to problems from noise, lack of distinctive high-frequency feature information, mesh parametrization problems etc. Our method enables us to localize objects of interest for more purposeful meshing and subsequent scene understanding.

Download in pdf format
  author = {Jan Knopp and Mukta Prasad and Luc Van Gool },
  title = {Scene Cut: Class-specific Object Detection and Segmentation in 3D Scenes},
  booktitle = {Proc. 3DIMPVT},
  year = {2011},
  month = {May},
  pages = {180-187},
  publisher = {IEEE Computer Society},
  keywords = {Hough Transform, Min-Cut, segmentation, detection, ISM, localization}