Shape Completion Using Deep Boltzmann Machine

Shape completion is an important task in the field of image processing. An alternative method is to capture the shape information and finish the completion by a generative model, such as Deep Boltzmann Machine. With its powerful ability to deal with the distribution of the shapes, it is quite easy to acquire the result by sampling from the model. In this paper, we make use of the hidden activation of the DBM and incorporate it with the convolutional shape features to fit a regression model. We compare the output of the regression model with the incomplete shape feature in order to set a proper and compact mask for sampling from the DBM. The experiment shows that our method can obtain realistic results without any prior information about the incomplete object shape.

[1]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[2]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[3]  Ruslan Salakhutdinov,et al.  Learning Deep Boltzmann Machines using Adaptive MCMC , 2010, ICML.

[4]  Truong Q. Nguyen,et al.  Spatio-temporal texture synthesis and image inpainting for video applications , 2005, IEEE International Conference on Image Processing 2005.

[5]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[6]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[7]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[8]  Hugo Larochelle,et al.  An Infinite Restricted Boltzmann Machine , 2015, Neural Computation.

[9]  Ruslan Salakhutdinov,et al.  On the quantitative analysis of deep belief networks , 2008, ICML '08.

[10]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[11]  Christopher K. I. Williams,et al.  Multiple Texture Boltzmann Machines , 2012, AISTATS.

[12]  Jian Sun,et al.  Image Completion Approaches Using the Statistics of Similar Patches , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Ruslan Salakhutdinov,et al.  Learning in Markov Random Fields using Tempered Transitions , 2009, NIPS.

[14]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[15]  Michael I. Jordan,et al.  Mean Field Theory for Sigmoid Belief Networks , 1996, J. Artif. Intell. Res..

[16]  Geoffrey E. Hinton,et al.  Using fast weights to improve persistent contrastive divergence , 2009, ICML '09.

[17]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[18]  Benjamin B. Kimia,et al.  Euler Spiral for Shape Completion , 2003, International Journal of Computer Vision.

[19]  Yoshua Bengio,et al.  A Spike and Slab Restricted Boltzmann Machine , 2011, AISTATS.

[20]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[21]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[22]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Christopher K. I. Williams,et al.  The Shape Boltzmann Machine: A Strong Model of Object Shape , 2012, International Journal of Computer Vision.

[24]  Hugo Larochelle,et al.  Efficient Learning of Deep Boltzmann Machines , 2010, AISTATS.