MSCE: An edge preserving robust loss function for improving super-resolution algorithms (original) (raw)

Prof. International Conf. on Neural Information Processing (ICONIP 2018), 2018

Abstract

With the recent advancement in the deep learning technologies such as CNNs and GANs, there is signi ficant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques. In this work, we propose a robust loss function based on the preservation of edges obtained by the Canny operator. This loss function, when combined with the existing loss function such as mean square error (MSE), gives better SR reconstruction measured in terms of PSNR and SSIM. Our proposed loss function guarantees improved performance on any existing algorithm using MSE loss function, without any increase in the computational complexity during testing.

Ramakrishnan Angarai Ganesan hasn't uploaded this paper.

Let Ramakrishnan know you want this paper to be uploaded.

Ask for this paper to be uploaded.