Stark, Michael Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;
http://www.visionmeetscognition.org/fpic2014/Camera_Ready/Paper%208.pdf (Any fulltext)
Zia, M. Z., Stark, M., & Schindler, K. (2014). Physically Grounded 3D Scene Interpretation with Detailed Object Models. In Vision Meets Cognition Workshop: Functionality, Physics, Intentionality, and Causality.