Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left">Methods</td><td class="align_center">City</td><td class="align_center">Calendar</td><td class="align_center">Foliage</td><td class="align_center">Walk</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">Bicubic interpolation</td><td class="align_center">25.84</td><td class="align_center">20.30</td><td class="align_center">24.13</td><td class="align_center">26.47</td></tr><tr><td class="align_left">Our method</td><td class="align_center">30.44</td><td class="align_center">23.59</td><td class="align_center">29.00</td><td class="align_center">32.61</td></tr><tr><td class="align_left">ESPCN</td><td class="align_center">30.29</td><td class="align_center">23.56</td><td class="align_center">28.83</td><td class="align_center">32.49</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Improvement of PSNR (dB) value of video frame by motion estimation.</div>

Wireless Communications and Mobile Computing

tab2

Table 2

Table 2: Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing 