Citation
V. G. Kim, S. Chaudhuri, L. Guibas, T. Funkhouser. "Shape2Pose: Human-Centric Shape Analysis". ACM Transactions on Graphics (SIGGRAPH), 2014.

Abstract
As 3D acquisition devices and modeling tools become widely available there is a growing need for automatic algorithms that analyze the semantics and functionality of digitized shapes. Most recent research has focused on analyzing geometric structures of shapes. Our work is motivated by the observation that a majority of manmade shapes are designed to be used by people. Thus, in order to fully understand their semantics, one needs to answer a fundamental question: “how do people interact with these objects?” As an initial step towards this goal, we offer a novel algorithm for automatically predicting a static pose that a person would need to adopt in order to use an object. Specifically, given an input 3D shape, the goal of our analysis is to predict a corresponding human pose, including contact points and kinematic parameters. This is especially challenging for man-made objects that commonly exhibit a lot of variance in their geometric structure. We address this challenge by observing that contact points usually share consistent local geometric features related to the anthropometric properties of corresponding parts and that human body is subject to kinematic constraints and priors. Accordingly, our method effectively combines local region classification and global kinematically-constrained search to successfully predict poses for various objects. We also evaluate our algorithm on six diverse collections of 3D polygonal models (chairs, gym equipment, cockpits, carts, bicycles, and bipedal devices) containing a total of 147 models. Finally, we demonstrate that the poses predicted by our algorithm can be used in several shape analysis problems, such as establishing correspondences between objects, detecting salient regions, finding informative viewpoints, and retrieving functionally-similar shapes.

Electronic downloads

• 14_SIGGRAPH_Shape2Pose.pdf · application/pdf · 2065 kbytes

• HTML

  V. G. Kim, S. Chaudhuri, L. Guibas, T. Funkhouser. <a
  href="http://robotics.eecs.berkeley.edu/pubs/18.html"
  >Shape2Pose: Human-Centric Shape Analysis</a>, ACM
  Transactions on Graphics (SIGGRAPH), 2014.

• Plain text

  V. G. Kim, S. Chaudhuri, L. Guibas, T. Funkhouser.
  "Shape2Pose: Human-Centric Shape Analysis". ACM
  Transactions on Graphics (SIGGRAPH), 2014.

• BibTeX

  @inproceedings{KimChaudhuriGuibasFunkhouser14_Shape2PoseHumanCentricShapeAnalysis,
      author = {V. G. Kim and S. Chaudhuri and L. Guibas and T.
                Funkhouser},
      title = {Shape2Pose: Human-Centric Shape Analysis},
      booktitle = {ACM Transactions on Graphics (SIGGRAPH)},
      year = {2014},
      abstract = {As 3D acquisition devices and modeling tools
                become widely available there is a growing need
                for automatic algorithms that analyze the
                semantics and functionality of digitized shapes.
                Most recent research has focused on analyzing
                geometric structures of shapes. Our work is
                motivated by the observation that a majority of
                manmade shapes are designed to be used by people.
                Thus, in order to fully understand their
                semantics, one needs to answer a fundamental
                question: �how do people interact with these
                objects?� As an initial step towards this goal,
                we offer a novel algorithm for automatically
                predicting a static pose that a person would need
                to adopt in order to use an object. Specifically,
                given an input 3D shape, the goal of our analysis
                is to predict a corresponding human pose,
                including contact points and kinematic parameters.
                This is especially challenging for man-made
                objects that commonly exhibit a lot of variance in
                their geometric structure. We address this
                challenge by observing that contact points usually
                share consistent local geometric features related
                to the anthropometric properties of corresponding
                parts and that human body is subject to kinematic
                constraints and priors. Accordingly, our method
                effectively combines local region classification
                and global kinematically-constrained search to
                successfully predict poses for various objects. We
                also evaluate our algorithm on six diverse
                collections of 3D polygonal models (chairs, gym
                equipment, cockpits, carts, bicycles, and bipedal
                devices) containing a total of 147 models.
                Finally, we demonstrate that the poses predicted
                by our algorithm can be used in several shape
                analysis problems, such as establishing
                correspondences between objects, detecting salient
                regions, finding informative viewpoints, and
                retrieving functionally-similar shapes.},
      URL = {http://robotics.eecs.berkeley.edu/pubs/18.html}
  }
  

Posted by Ehsan Elhamifar on 7 Jun 2014.
Groups: ehumans
For additional information, see the Publications FAQ or contact webmaster at robotics eecs berkeley edu.