MSCE: An edge preserving robust loss function for improving super-resolution algorithms
This work addresses the need for enhanced image super-resolution for applications like medical imaging or photography, but it is incremental as it builds on existing methods without major paradigm shifts.
The authors tackled the problem of improving super-resolution image quality by proposing a new edge-preserving loss function based on the Canny operator, which when combined with MSE loss, achieved better reconstruction results with higher PSNR and SSIM scores.
With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant 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.