Color Enhancement Using Global Parameters and Local Features Learning

Liu, Enyu; Li, Songnan; Liu, Shan

doi:10.1007/978-3-030-69532-3_13

Cited by 12 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods usually use a lowresolution image to extract features and predict the parameters of some predefined global or local color transformation, and later apply the predicted color transformation to the original high-resolution image. Different color transformations have been used in existing works, including quadratic transforms [46,7,32,41], local affine transforms [11], curve based transforms [6,13,29,23,36], filters [10,35], lookup tables [49,43], and customized transforms [5]. Compared with image-toimage translation based methods, these methods usually use smaller models and are more efficient.…”

Section: Sequential Imagementioning

confidence: 99%

See 1 more Smart Citation

Neural Color Operators for Sequential Image Retouching

Wang¹,

Li²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

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.Code is available at https://github.com/amberwangyili/neurop.

show abstract

Section: Sequential Imagementioning

confidence: 99%

“…where ∇(•) denotes the gradient operator. Besides, we include a color loss [32,42], which regards RGB colors as 3D vectors and measures their angular differences. Specifically, the color loss is defined as:…”

Section: Loss Function and Trainingmentioning

confidence: 99%

Neural Color Operators for Sequential Image Retouching

Wang¹,

Li²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, these methods employ CNNs on a low-resolution, fixed-size version of the input image to predict image-adaptive parameters of some specific color transform functions. Typical color transform functions include affine transformation matrices [9,32,3,23], curve-based functions [25,31,18,17,21,11,14,26,1], multi-layer perceptrons (MLPs) [12] and 3D LUTs [36,33]. These learned transform functions can adapt to different input Id Layer Output Shape…”

Section: Image Enhancementmentioning

confidence: 99%

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

Yang¹,

Jin²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a single type of LUTs, either 1D or 3D, in a coupled manner. This scheme raises a dilemma of improving model expressiveness or efficiency due to two factors. On the one hand, the 1D LUTs provide high computational efficiency but lack the critical capability of color components interaction. On the other, the 3D LUTs present enhanced component-correlated transform capability but suffer from heavy memory footprint, high training difficulty, and limited cell utilization. Inspired by the conventional divide-and-conquer practice in the image signal processor, we present SepLUT (separable image-adaptive lookup table) to tackle the above limitations. Specifically, we separate a single color transform into a cascade of componentindependent and component-correlated sub-transforms instantiated as 1D and 3D LUTs, respectively. In this way, the capabilities of two subtransforms can facilitate each other, where the 3D LUT complements the ability to mix up color components, and the 1D LUT redistributes the input colors to increase the cell utilization of the 3D LUT and thus enable the use of a more lightweight 3D LUT. Experiments demonstrate that the proposed method presents enhanced performance on photo retouching benchmark datasets than the current state-of-the-art and achieves real-time processing on both GPUs and CPUs.

show abstract

“…There are roughly three categories of functions to follow: color transformation matrix [5,12,31], curve-based color transformation function [15,24,29,38], and 3D lookup table (LUT) [49].…”

Section: Prior Artmentioning

confidence: 99%

“…The curve encoder predicts the curves' parameters from the low-resolution version of the image, and the enhancer applies these curves to transform the fullresolution image. Unlike the existing color transform-based image enhancement methods [5,12,24,28,31,38,46,49], StarEnhancer considers the correlation between color channels and the pixel's coordinates.…”

Section: Introductionmentioning

confidence: 99%

StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement

Song

Qian

2021

Preprint

View full text Add to dashboard Cite

Image enhancement is a subjective process whose targets vary with user preferences. In this paper, we propose a deep learning-based image enhancement method covering multiple tonal styles using only a single model dubbed StarEnhancer. It can transform an image from one tonal style to another, even if that style is unseen. With a simple one-time setting, users can customize the model to make the enhanced images more in line with their aesthetics. To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS. Finally, our proposed enhancement method has good interactability, which allows the user to fine-tune the enhanced image using intuitive options.

show abstract

Color Enhancement Using Global Parameters and Local Features Learning

Cited by 12 publications

References 25 publications

Neural Color Operators for Sequential Image Retouching

Neural Color Operators for Sequential Image Retouching

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement

Contact Info

Product

Resources

About