Slide 6
Slide 6 text
Abstract (2/3)
6
We further show that traditional sparse-coding-based
SR methods can also be viewed as a deep convolutional
network. But unlike traditional methods that handle
each component separately, our method jointly
optimizes all layers. Our deep CNN has a lightweight
structure, yet demonstrates state-of-the-art restoration
quality, and achieves fast speed for practical on-line
usage.
・従来の超解像も、深いCNNの一種と捉えられることを示す
・ただ、従来の手法では構成要素ごと個別に扱っていたが、
提案手法は全ての階層をまとめて最適化する
・我々のCNNは軽量な構造だが、修復の品質はSOTAで高速