Frequency Domain Loss Function for Deep Exposure Correction of Dark Images

04/22/2021
by   Ojasvi Yadav, et al.
0

We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct choice of thresholds, frequency estimates etc. On the other hand, traditional deep networks are trained end-to-end in the RGB space by formulating this task as an image-translation problem. However, that is done without any explicit constraints on the inherent noise of the dark images and thus produce noisy and blurry outputs. To this end we propose a DCT/FFT based multi-scale loss function, which when combined with traditional losses, trains a network to translate the important features for visually pleasing output. Our loss function is end-to-end differentiable, scale-agnostic, and generic; i.e., it can be applied to both RAW and JPEG images in most existing frameworks without additional overhead. Using this loss function, we report significant improvements over the state-of-the-art using quantitative metrics and subjective tests.

READ FULL TEXT
research
04/22/2022

Exposure Correction Model to Enhance Image Quality

Exposure errors in an image cause a degradation in the contrast and low ...
research
04/16/2019

End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks

When taking photos in dim-light environments, due to the small amount of...
research
06/26/2020

A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model

To train Variational Autoencoders (VAEs) to generate realistic imagery r...
research
03/12/2022

VAFO-Loss: VAscular Feature Optimised Loss Function for Retinal Artery/Vein Segmentation

Estimating clinically-relevant vascular features following vessel segmen...
research
12/23/2020

Focal Frequency Loss for Generative Models

Despite the remarkable success of generative models in creating photorea...
research
06/04/2018

Synthetic data generation for end-to-end thermal infrared tracking

The usage of both off-the-shelf and end-to-end trained deep networks hav...
research
04/18/2017

Unsupervised Learning by Predicting Noise

Convolutional neural networks provide visual features that perform remar...

Please sign up or login with your details

Forgot password? Click here to reset