Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter

Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
复制标题

具有基于主动学习的本地过滤器的众包照片增强功能

DOI:
10.1109/tcsvt.2023.3233989
复制
发表时间:
2023
影响因子:
8.4
通讯作者:
Toshihiko Yamasaki
Toshihiko Yamasaki
中科院分区:
工程技术1区
文献类型:
--
作者:
Satoshi Kosugi;Toshihiko Yamasaki

文献摘要

参考文献

相似文献

在这项研究中,我们解决了局部照片增强,以提高输入图像的美学质量,通过应用不同的效果到不同的区域。现有的照片增强方法要么不是内容感知的,要么不是本地的,因此,我们提出了一个群众供电的本地增强方法,内容感知的本地增强,这是通过要求群众工作者本地优化参数的图像编辑功能。为了使其更容易局部优化的参数,我们提出了一种基于主动学习的局部滤波器。仅需要在通过主动学习方法选择的几个关键像素处确定参数,并且使用回归模型自动预测其他像素处的参数。所选关键像素处的参数被独立优化,从而将优化问题分解为一系列单滑块调整。我们的实验表明,该滤波器的性能优于现有滤波器,并且我们的增强结果比现有增强方法的结果在视觉上更令人愉悦。我们的源代码和结果可以在https://github.com/satoshi-kosugi/crowd-powered上找到。
In this study, we address local photo enhancement to improve the aesthetic quality of an input image by applying different effects to different regions. Existing photo enhancement methods are either not content-aware or not local; therefore, we propose a crowd-powered local enhancement method for content-aware local enhancement, which is achieved by asking crowd workers to locally optimize parameters for image editing functions. To make it easier to locally optimize the parameters, we propose an active learning based local filter. The parameters need to be determined at only a few key pixels selected by an active learning method, and the parameters at the other pixels are automatically predicted using a regression model. The parameters at the selected key pixels are independently optimized, breaking down the optimization problem into a sequence of single-slider adjustments. Our experiments show that the proposed filter outperforms existing filters, and our enhanced results are more visually pleasing than the results by the existing enhancement methods. Our source code and results are available at https://github.com/satoshi-kosugi/crowd-powered .
DOI: 10.1109/cvpr42600.2020.01284
发表时间: 2020-03
期刊: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
S. Moran;Pierre Marza;Steven G. McDonagh;Sarah Parisot;G. Slabaugh
通讯作者: S. Moran;Pierre Marza;Steven G. McDonagh;Sarah Parisot;G. Slabaugh
DOI: 10.1609/aaai.v34i07.6790
发表时间: 2019-12
期刊: --
影响因子: --
作者:
Satoshi Kosugi;T. Yamasaki
通讯作者: Satoshi Kosugi;T. Yamasaki
EGAL:TCBR 探索引导主动学习
DOI: 10.1007/978-3-642-14274-1_13
发表时间: 2010
影响因子: 5.3
作者:
Rong Hu;Sarah Jane Delany;Brian Mac Namee
通讯作者: Brian Mac Namee
用于交互式视觉设计优化的顺序画廊
DOI: 10.1145/3386569.3392444
发表时间: 2020
期刊: ACM Transactions on Graphics (TOG)
影响因子: --
作者:
Yuki Koyama;Issei Sato;Masataka Goto
通讯作者: Masataka Goto
用于低光图像增强的结构-纹理感知网络
DOI: 10.1109/tcsvt.2022.3141578
发表时间: 2022
影响因子: 8.4
作者:
Kai Xu;H. Chen;Chunmei Xu;Yi Jin;C. Zhu
通讯作者: C. Zhu