Timezone: »

Nonparametric Bayesian Texture Learning and Synthesis
Leo Zhu · Yuanhao Chen · Bill Freeman · Antonio Torralba

Mon Dec 07 07:00 PM -- 11:59 PM (PST) @

We present a nonparametric Bayesian method for texture learning and synthesis. A texture image is represented by a 2D-Hidden Markov Model (2D-HMM) where the hidden states correspond to the cluster labeling of textons and the transition matrix encodes their spatial layout (the compatibility between adjacent textons). 2D-HMM is coupled with the Hierarchical Dirichlet process (HDP) which allows the number of textons and the complexity of transition matrix grow as the input texture becomes irregular. The HDP makes use of Dirichlet process prior which favors regular textures by penalizing the model complexity. This framework (HDP-2D-HMM) learns the texton vocabulary and their spatial layout jointly and automatically. The HDP-2D-HMM results in a compact representation of textures which allows fast texture synthesis with comparable rendering quality over the state-of-the-art image-based rendering methods. We also show that HDP-2D-HMM can be applied to perform image segmentation and synthesis.

Author Information

Leo Zhu
Yuanhao Chen (University of California, Los Angeles)
Bill Freeman (MIT/Google)
Antonio Torralba (Massachusetts Institute of Technology)

More from the Same Authors