Super-Resolution 2.2 Convolutional Neural Networks 2.3 Deep Learning for Image Restoration 3 CONVOLUTIONAL NEURAL NETWORKS FOR SUPER-RESOLUTION 3.1 Formulation 3.2 Relationship to Sparse-Coding-Based Methods 3.3 Training 4 EXPERIMENTS 4.1 Training Data 4.2 Learned Filters for Super-Resolution 4.3 Model and Performance Trade-offs 4.4 Comparisons to State-of-the-Arts 4.5 Experiments on Color Channels 5 CONCLUSION REFERENCES
single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low- resolution image as the input and outputs the high- resolution one. ・単一イメージの超解像の、深層学習による手法を提案 ・提案手法はend-to-endで高/低解像度の画像の対応を学習 ・その対応は、深い畳み込みニューラルネットワークで表現 ・低解像度の画像を入力とし、高解像度の画像を出力する
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
settings to achieve tradeoffs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality. ・異なるネットワーク構造やパラメータ設定でも評価 ・それらは、性能と実行速度とのトレードオフ ・さらに、ネットワークをカラー3チャネル同時処理に拡張 ・かつ(入力画像の)再構成については、全体として高品質