Super-Resolution with Horizontal and Vertical Convolutional Neural Networks
Yu Kato, Shinya Ohtani, Nobutaka Kuroki, Tetsuya Hirose, Masahiro Numa · IEEJ Transactions on Electronics Information and Systems · 2018
This paper proposes an image super-resolution technique with convolutional neural networks using horizontal and vertical filters. In the proposed method, calculation costs become small because square filters at a hidden layer are replaced with horizontal and vertical bar filters. Experimental results have shown that the average processing time for the proposed architecture was only a half of the conventional one while keeping high image qualities.