DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting

TL;DR

This paper introduces DCIL, a unified framework leveraging deep internal and contextual learning for various image restoration and retargeting tasks, demonstrating effectiveness across multiple challenging scenarios.

Contribution

It proposes a novel general framework that combines internal and contextual feature learning for image restoration and retargeting, bridging different unsupervised approaches.

Findings

Effective in classical image resize and super-resolution tasks

Handles noisy low-resolution images successfully

Outperforms relevant state-of-the-art methods

Abstract

Recently, there is a vast interest in developing methods which are independent of the training samples such as deep image prior, zero-shot learning, and internal learning. The methods above are based on the common goal of maximizing image features learning from a single image despite inherent technical diversity. In this work, we bridge the gap between the various unsupervised approaches above and propose a general framework for image restoration and image retargeting. We use contextual feature learning and internal learning to improvise the structure similarity between the source and the target images. We perform image resize application in the following setups: classical image resize using super-resolution, a challenging image resize where the low-resolution image contains noise, and content-aware image resize using image retargeting. We also provide comparisons to the relevant state-of-the-art methods.