chenpingjun1990

  C++博客 :: 首页 :: 新随笔 :: 联系 :: 聚合  :: 管理 ::
  0 随笔 :: 22 文章 :: 5 评论 :: 0 Trackbacks
       A good model of object shape is essential in application such as segmentation, object detection, inpainting and 
graphics, etc.
       In this paper, we use a type of Deep Boltzmann Machine that we call a Shape Boltzmann Machine (ShapeBM) for the task of modeling binary shape images.
       This paper define a strong model should meets two requirements:Realism/Generalization.
        Previous approaches to modeling 2D shape:1.Grid MRF/CRF 2.PCA/Factor Analysis 3.template shapes 4.Shape fragments.
        The main contribution of this paper is to show how a strong model of binary shape can be constructed using a form of DBM,We demonstrate that a ShapeBM trained on a relatively small dataset is both able to generate realistic samples and to generalize to generate samples that differ form images in the training dataset.


/Files/chenpingjun1990/cvpr_12_Shape_Boltzmann_Machine.pdf

/Files/chenpingjun1990/cvpr_12_eslami_shapebm_code.zip

"The Shape Boltzmann Machine: a Strong Model of Object Shape" 
Eslami, S.M., Heess, N.Winn, J.
Computer Vision and Pattern Recognition (CVPR), June 2012. 
posted on 2012-07-11 11:03 万川先生 阅读(259) 评论(0)  编辑 收藏 引用 所属分类: VisionPaper