图像色彩增强相关论文阅读-Representative Color Transform for Image Enhancement(ICCV2021)

原创

于 2023-06-26 20:35:24 发布 · 1.4k 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#论文阅读

文章提出了一种名为RepresentativeColorTransform(RCT)的新方法，用于解决图像增强中的细节丢失和固定输入尺寸问题。RCT通过学习大规模色彩迁移，利用输入图像的颜色表征来估计变换颜色，进而根据颜色相似性增强图像。相比于传统的encode-decode结构，RCT能更好地保留细节，并适用于任意分辨率的图像。实验表明，该方法在多个数据集上表现出色，提高了色彩强化的效果。

文章目录

Representative Color Transform for Image Enhancement
Abstract
Introduction
Related work
Method
实验
Conclusion

Representative Color Transform for Image Enhancement

作者：Hanul Kim1, Su-Min Choi2, Chang-Su Kim3, Yeong Jun Koh
单位：Seoul National University of Science and Technology 2Chungnam National University 3Korea University

Abstract

前人方法都是encode-decode方式，丢失细节；密集转化也限制颜色空间的迁移效果；
本文使用颜色迁移表征（RCT）表征颜色变化，根据输入和表征颜色相似性增强颜色，得到更好效果；
RCT determines different representative colors specialized in in- put images and estimates transformed colors for the repre- sentative colors. It then determines enhanced colors us- ing these transformed colors based on the similarity be- tween input and representative colors.

Introduction

问题
First, details of the input im- age are not preserved in the up-sampling process of the de- coder, even though they employ skip-connections. Second, these approaches train networks with fixe