Neural Color Operators for Sequential Image Retouching
- URL: http://arxiv.org/abs/2207.08080v1
- Date: Sun, 17 Jul 2022 05:33:19 GMT
- Title: Neural Color Operators for Sequential Image Retouching
- Authors: Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding
- Abstract summary: 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.
Our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities.
- Score: 62.99812889713773
- License: http://creativecommons.org/licenses/by/4.0/
- 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 data will be made
publicly available.
Related papers
- Multispectral Texture Synthesis using RGB Convolutional Neural Networks [2.3213238782019316]
State-of-the-art RGB texture synthesis algorithms rely on style distances that are computed through statistics of deep features.
We propose two solutions to extend these methods to multispectral imaging.
arXiv Detail & Related papers (2024-10-21T13:49:54Z) - Transforming Color: A Novel Image Colorization Method [8.041659727964305]
This paper introduces a novel method for image colorization that utilizes a color transformer and generative adversarial networks (GANs)
The proposed method integrates a transformer architecture to capture global information and a GAN framework to improve visual quality.
Experimental results show that the proposed network significantly outperforms other state-of-the-art colorization techniques.
arXiv Detail & Related papers (2024-10-07T07:23:42Z) - Color Equivariant Convolutional Networks [50.655443383582124]
CNNs struggle if there is data imbalance between color variations introduced by accidental recording conditions.
We propose Color Equivariant Convolutions ( CEConvs), a novel deep learning building block that enables shape feature sharing across the color spectrum.
We demonstrate the benefits of CEConvs in terms of downstream performance to various tasks and improved robustness to color changes, including train-test distribution shifts.
arXiv Detail & Related papers (2023-10-30T09:18:49Z) - Incorporating Ensemble and Transfer Learning For An End-To-End
Auto-Colorized Image Detection Model [0.0]
This paper presents a novel approach that combines the advantages of transfer and ensemble learning approaches to help reduce training time and resource requirements.
The proposed model shows promising results, with accuracy ranging from 94.55% to 99.13%.
arXiv Detail & Related papers (2023-09-25T19:22:57Z) - Neural Preset for Color Style Transfer [46.66925849502683]
We present a Neural Preset technique to address the limitations of existing color style transfer methods.
Our method is based on two core designs. First, we propose Deterministic Neural Color Mapping (DNCM) to consistently operate on each pixel.
Second, we develop a two-stage pipeline by dividing the task into color normalization and stylization.
arXiv Detail & Related papers (2023-03-23T17:59:10Z) - Permutation Equivariant Neural Functionals [92.0667671999604]
This work studies the design of neural networks that can process the weights or gradients of other neural networks.
We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order.
In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
arXiv Detail & Related papers (2023-02-27T18:52:38Z) - Name Your Colour For the Task: Artificially Discover Colour Naming via
Colour Quantisation Transformer [62.75343115345667]
We propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining machine recognition on the quantised images.
We observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages.
Our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage.
arXiv Detail & Related papers (2022-12-07T03:39:18Z) - Detecting Recolored Image by Spatial Correlation [60.08643417333974]
Image recoloring is an emerging editing technique that can manipulate the color values of an image to give it a new style.
In this paper, we explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring.
Our method achieves the state-of-the-art detection accuracy on multiple benchmark datasets and exhibits well generalization for unknown types of recoloring methods.
arXiv Detail & Related papers (2022-04-23T01:54:06Z) - Structure-Preserving Multi-Domain Stain Color Augmentation using
Style-Transfer with Disentangled Representations [0.9051352746190446]
HistAuGAN can simulate a wide variety of realistic histology stain colors, thus making neural networks stain-invariant when applied during training.
Based on a generative adversarial network (GAN) for image-to-image translation, our model disentangles the content of the image, i.e., the morphological tissue structure, from the stain color attributes.
It can be trained on multiple domains and, therefore, learns to cover different stain colors as well as other domain-specific variations introduced in the slide preparation and imaging process.
arXiv Detail & Related papers (2021-07-26T17:52:39Z) - Supervised and Unsupervised Learning of Parameterized Color Enhancement [112.88623543850224]
We tackle the problem of color enhancement as an image translation task using both supervised and unsupervised learning.
We achieve state-of-the-art results compared to both supervised (paired data) and unsupervised (unpaired data) image enhancement methods on the MIT-Adobe FiveK benchmark.
We show the generalization capability of our method, by applying it on photos from the early 20th century and to dark video frames.
arXiv Detail & Related papers (2019-12-30T13:57:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.