Neural Color Operators for Sequential Image Retouching

TL;DR

This paper introduces a lightweight neural color operator framework for sequential image retouching, which learns pixelwise color transformations with controllable strength, outperforming state-of-the-art methods in quality and flexibility.

Contribution

It presents a novel neural color operator model that mimics traditional color operators, incorporating equivariant mapping and a high-dimensional translation for effective color transformation.

Findings

Achieves state-of-the-art results on public datasets.

Offers flexible control over retouching strength.

Demonstrates superior visual quality and quantitative performance.

Abstract

We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism property of color operators, we employ equivariant mapping and adopt an encoder-decoder structure which maps the non-linear color transformation to a much simpler transformation (i.e., translation) in a high dimensional space. The scalar strength of each neural color operator is predicted using CNN based strength predictors by analyzing global image statistics. Overall, our method is rather lightweight and offers flexible controls. Experiments and user studies on public datasets show that our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities. The code and pretrained models are provided at https://github.com/amberwangyili/neurop