Cascading and Residual Connected Network for Single Image Superresolution

<div>×3 SR’s loss function comparison. In the first row, it is the <i>comic</i> images in the Set14 dataset. The image processed with <svg height="11.9087pt" id="M48" style="vertical-align:-3.2728pt" version="1.1" viewbox="-0.0498162 -8.6359 47.9686 11.9087" width="47.9686pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M541 160L512 170C485 116 462 88 439 67C411 41 376 35 318 35C272 35 238 37 224 48C207 61 205 85 212 121L290 533C305 611 308 615 391 622L397 650H139L133 622C217 615 221 612 206 533L126 118C111 41 103 34 23 26L17 0H474C489 31 528 124 541 160Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,8.294,3.132)"><path d="M389 0V32C297 38 291 46 291 118V635C234 613 175 595 109 583V556L161 554C203 552 207 547 207 497V118C207 46 201 38 110 32V0H389Z"></path></g><g transform="matrix(.013,0,0,-0.013,16.146,0)"><path d="M535 230V280H323V490H265V280H52V230H265V-3H323V230H535Z"></path></g><g transform="matrix(.013,0,0,-0.013,26.682,0)"><path d="M541 160L512 170C485 116 462 88 439 67C411 41 376 35 318 35C272 35 238 37 224 48C207 61 205 85 212 121L290 533C305 611 308 615 391 622L397 650H139L133 622C217 615 221 612 206 533L126 118C111 41 103 34 23 26L17 0H474C489 31 528 124 541 160Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,34.976,3.132)"><path d="M592 498C586 556 582 629 581 675H560C545 656 537 650 510 650H115C87 650 74 652 60 675H40C38 620 33 555 28 495H57C69 539 77 568 89 585C102 607 122 616 205 616H267V123C267 44 259 34 168 28V0H454V28C360 34 352 44 352 123V616H422C498 616 514 608 531 584C542 568 552 543 562 495L592 498Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,40.838,3.132)"><path d="M687 650H462V622C543 612 549 605 530 547C498 447 422 252 372 126H370C302 298 229 492 204 563C188 607 191 615 262 622V650H17V622C77 616 93 608 122 534C180 389 262 172 329 -11H360C436 196 541 450 568 516C606 605 619 614 687 622V650Z"></path></g></svg> has precise details in the area around the eyes. The bottom line is the “img020” images in the Urban100 benchmark dataset. This method applies the <svg height="11.9087pt" id="M49" style="vertical-align:-3.2728pt" version="1.1" viewbox="-0.0498162 -8.6359 47.9686 11.9087" width="47.9686pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M541 160L512 170C485 116 462 88 439 67C411 41 376 35 318 35C272 35 238 37 224 48C207 61 205 85 212 121L290 533C305 611 308 615 391 622L397 650H139L133 622C217 615 221 612 206 533L126 118C111 41 103 34 23 26L17 0H474C489 31 528 124 541 160Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,8.294,3.132)"><path d="M389 0V32C297 38 291 46 291 118V635C234 613 175 595 109 583V556L161 554C203 552 207 547 207 497V118C207 46 201 38 110 32V0H389Z"></path></g><g transform="matrix(.013,0,0,-0.013,16.146,0)"><path d="M535 230V280H323V490H265V280H52V230H265V-3H323V230H535Z"></path></g><g transform="matrix(.013,0,0,-0.013,26.682,0)"><path d="M541 160L512 170C485 116 462 88 439 67C411 41 376 35 318 35C272 35 238 37 224 48C207 61 205 85 212 121L290 533C305 611 308 615 391 622L397 650H139L133 622C217 615 221 612 206 533L126 118C111 41 103 34 23 26L17 0H474C489 31 528 124 541 160Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,34.976,3.132)"><path d="M592 498C586 556 582 629 581 675H560C545 656 537 650 510 650H115C87 650 74 652 60 675H40C38 620 33 555 28 495H57C69 539 77 568 89 585C102 607 122 616 205 616H267V123C267 44 259 34 168 28V0H454V28C360 34 352 44 352 123V616H422C498 616 514 608 531 584C542 568 552 543 562 495L592 498Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,40.838,3.132)"><path d="M687 650H462V622C543 612 549 605 530 547C498 447 422 252 372 126H370C302 298 229 492 204 563C188 607 191 615 262 622V650H17V622C77 616 93 608 122 534C180 389 262 172 329 -11H360C436 196 541 450 568 516C606 605 619 614 687 622V650Z"></path></g></svg> method to reconstruct the clear details, such as the windows.</div>

Wireless Communications and Mobile Computing

fig5

Figure 5

Figure 5: Cascading and Residual Connected Network for Single Image Superresolution 