Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping

TL;DR

This paper introduces a unified deep learning framework that uses a fixed pretrained CNN to ensure feature consistency across various image transformations, effectively addressing downscaling, decolorization, and HDR tone mapping.

Contribution

It is the first to unify multiple image processing tasks using deep feature consistency with a single CNN-based approach.

Findings

Demonstrates state-of-the-art performance in image downscaling

Achieves high-quality decolorization results

Effectively performs HDR tone mapping

Abstract

Building on crucial insights into the determining factors of the visual integrity of an image and the property of deep convolutional neural network (CNN), we have developed the Deep Feature Consistent Deep Image Transformation (DFC-DIT) framework which unifies challenging one-to-many mapping image processing problems such as image downscaling, decolorization (colour to grayscale conversion) and high dynamic range (HDR) image tone mapping. We train one CNN as a non-linear mapper to transform an input image to an output image following what we term the deep feature consistency principle which is enforced through another pretrained and fixed deep CNN. This is the first work that uses deep learning to solve and unify these three common image processing tasks. We present experimental results to demonstrate the effectiveness of the DFC-DIT technique and its state of the art performances.