Neural Color Operators for Sequential Image Retouching
This provides a lightweight and flexible method for image retouching, though it appears incremental as it builds on traditional color operators with neural adaptations.
The authors tackled the problem of image retouching by modeling it as a sequence of trainable neural color operators, achieving state-of-the-art results in quantitative measures and visual quality on public datasets.
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