MSCE: An edge preserving robust loss function for improving super-resolution algorithms

08/25/2018
by   Ram Krishna Pandey, et al.
0

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.

READ FULL TEXT
research
11/21/2019

Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss

Single image super-resolution (SISR) is the task of inferring a high-res...
research
07/30/2020

Very Deep Super-Resolution of Remotely Sensed Images with Mean Square Error and Var-norm Estimators as Loss Functions

In this work, very deep super-resolution (VDSR) method is presented for ...
research
01/18/2021

Fast and accurate learned multiresolution dynamical downscaling for precipitation

This study develops a neural network-based approach for emulating high-r...
research
01/02/2020

A Loss-Function for Causal Machine-Learning

Causal machine-learning is about predicting the net-effect (true-lift) o...
research
04/11/2021

Edge-Aware Image Compression using Deep Learning-based Super-resolution Network

We propose a learning-based compression scheme that envelopes a standard...
research
11/11/2020

Dense U-net for super-resolution with shuffle pooling layer

Single image super-resolution (SISR) in unconstrained environments is ch...
research
07/22/2023

Flight Contrail Segmentation via Augmented Transfer Learning with Novel SR Loss Function in Hough Space

Air transport poses significant environmental challenges, particularly t...

Please sign up or login with your details

Forgot password? Click here to reset