TY - GEN
T1 - Learning models of object structure
AU - Schlecht, Joseph
AU - Barnard, Kobus
PY - 2009
Y1 - 2009
N2 - We present an approach for learning stochastic geometric models of object categories from single view images. We focus here on models expressible as a spatially contiguous assemblage of blocks. Model topologies are learned across groups of images, and one or more such topologies is linked to an object category (e.g. chairs). Fitting learned topologies to an image can be used to identify the object class, as well as detail its geometry. The latter goes beyond labeling objects, as it provides the geometric structure of particular instances. We learn the models using joint statistical inference over category parameters, camera parameters, and instance parameters. These produce an image likelihood through a statistical imaging model. We use trans-dimensional sampling to explore topology hypotheses, and alternate between Metropolis-Hastings and stochastic dynamics to explore instance parameters. Experiments on images of furniture objects such as tables and chairs suggest that this is an effective approach for learning models that encode simple representations of category geometry and the statistics thereof, and support inferring both category and geometry on held out single view images.
AB - We present an approach for learning stochastic geometric models of object categories from single view images. We focus here on models expressible as a spatially contiguous assemblage of blocks. Model topologies are learned across groups of images, and one or more such topologies is linked to an object category (e.g. chairs). Fitting learned topologies to an image can be used to identify the object class, as well as detail its geometry. The latter goes beyond labeling objects, as it provides the geometric structure of particular instances. We learn the models using joint statistical inference over category parameters, camera parameters, and instance parameters. These produce an image likelihood through a statistical imaging model. We use trans-dimensional sampling to explore topology hypotheses, and alternate between Metropolis-Hastings and stochastic dynamics to explore instance parameters. Experiments on images of furniture objects such as tables and chairs suggest that this is an effective approach for learning models that encode simple representations of category geometry and the statistics thereof, and support inferring both category and geometry on held out single view images.
UR - http://www.scopus.com/inward/record.url?scp=84858727290&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84858727290&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84858727290
SN - 9781615679119
T3 - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
SP - 1615
EP - 1623
BT - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
PB - Neural Information Processing Systems
T2 - 23rd Annual Conference on Neural Information Processing Systems, NIPS 2009
Y2 - 7 December 2009 through 10 December 2009
ER -