Shape Completion Using Deep Boltzmann Machine

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/cin/volume-2017/5705693/figures/5705693.fig.002a.svgz" name="5705693.fig.002a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Training samples</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/cin/volume-2017/5705693/figures/5705693.fig.002b.svgz" name="5705693.fig.002b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Samples drawn from DBM</td></tr></table>

<div>(a) Some training samples used to train DBM. (b) Samples drawn from the trained DBM.</div>

Computational Intelligence and Neuroscience

fig2

Figure 2

Figure 2: Shape Completion Using Deep Boltzmann Machine 