DILIE: Deep Internal Learning for Image Enhancement
This work provides an incremental improvement in image enhancement for users dealing with hazy and noisy images.
This paper addresses the problem of enhancing image quality by transforming an input image into a perceptually improved version. The authors developed a deep internal learning framework that enhances both content and style features, utilizing a contextual content loss to preserve image context. The framework demonstrates superior performance compared to state-of-the-art methods for enhancing hazy and noisy images, as validated by structure similarity and perceptual error metrics.
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.