PiGraphs
Authors:
Open Access
- 11 July 2016
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 35 (4) , 1-12
Abstract
We learn a probabilistic model connecting human poses and arrangements of object geometry from real-world observations of interactions collected with commodity RGB-D sensors. This model is encoded as a set of prototypical interaction graphs (PiGraphs), a human-centric representation capturing physical contact and visual attention linkages between 3D geometry and human body parts. We use this encoding of the joint probability distribution over pose and geometry during everyday interactions to generate interaction snapshots , which are static depictions of human poses and relevant objects during human-object interactions. We demonstrate that our model enables a novel human-centric understanding of 3D content and allows for jointly generating 3D scenes and interaction poses given terse high-level specifications, natural language, or reconstructed real-world scene constraints.Keywords
Funding Information
- National Science Foundation (IIS-1514268)
This publication has 42 references indexed in Scilit:
- Real-time human pose recognition in parts from single depth imagesCommunications of the ACM, 2013
- Synthesis of concurrent object manipulation tasksACM Transactions on Graphics, 2012
- Motion graphs++ACM Transactions on Graphics, 2012
- Example-based synthesis of 3D object arrangementsACM Transactions on Graphics, 2012
- A probabilistic model for component-based shape synthesisACM Transactions on Graphics, 2012
- Make it homeACM Transactions on Graphics, 2011
- Motion patchesACM Transactions on Graphics, 2006
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Style-based inverse kinematicsACM Transactions on Graphics, 2004
- Modeling Objects for Interaction Tasks1999