DILIE: Deep Internal Learning for Image Enhancement

TL;DR

DILIE introduces a deep internal learning framework that enhances images by improving content and style features, effectively handling hazy and noisy images while outperforming existing methods in quality metrics.

Contribution

The paper presents a novel deep internal learning approach for image enhancement that leverages content and style feature enhancement with a new contextual content loss.

Findings

Outperforms state-of-the-art image enhancement methods

Effective on hazy and noisy images

Uses structure similarity and perceptual error for validation

Abstract

We consider the generic deep image enhancement problem where an input image is transformed into a perceptually better-looking image. Recent methods for image enhancement consider the problem by performing style transfer and image restoration. The methods mostly fall into two categories: training data-based and training data-independent (deep internal learning methods). We perform image enhancement in the deep internal learning framework. Our Deep Internal Learning for Image Enhancement framework enhances content features and style features and uses contextual content loss for preserving image context in the enhanced image. We show results on both hazy and noisy image enhancement. To validate the results, we use structure similarity and perceptual error, which is efficient in measuring the unrealistic deformation present in the images. We show that the proposed framework outperforms the relevant state-of-the-art works for image enhancement.