Neural Color Operators for Sequential Image Retouching
Preprint
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/neuropKeywords
All Related Versions
- Version 1, 2022-07-17, ArXiv
- Version 2, 2022-10-25, ArXiv
- Published version: , 38.
This publication has 15 references indexed in Scilit:
- Very Lightweight Photo Retouching Network With Conditional Sequential ModulationIEEE Transactions on Multimedia, 2022
- Learning Enriched Features for Fast Image Restoration and EnhancementIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- EnlightenGAN: Deep Light Enhancement Without Paired SupervisionIEEE Transactions on Image Processing, 2021
- Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-timeIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Towards Unsupervised Deep Image Enhancement With Generative Adversarial NetworkIEEE Transactions on Image Processing, 2020
- A Histogram Modification Framework and Its Application for Image Contrast EnhancementIEEE Transactions on Image Processing, 2009
- Image up-sampling using total-variation regularization with a new observation modelIEEE Transactions on Image Processing, 2005
- Adaptive image contrast enhancement using generalizations of histogram equalizationIEEE Transactions on Image Processing, 2000
- Image enhancement based on equal area dualistic sub-image histogram equalization methodIEEE Transactions on Consumer Electronics, 1999
- Contrast enhancement using brightness preserving bi-histogram equalizationIEEE Transactions on Consumer Electronics, 1997