基于主动学习局部滤波器的众包驱动照片增强
Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
AI总结：
针对现有照片增强方法缺乏内容感知或无法局部增强的问题，提出结合众包与主动学习局部滤波器的方法，通过众包优化关键像素参数、回归预测其余参数，实现更优的局部美学增强效果。
摘要：
本研究针对局部照片增强问题展开，旨在通过对图像不同区域施加不同效果来提升输入图像的美学质量。现有照片增强方法要么不具备内容感知能力，要么无法实现局部增强，因此我们提出了一种众包驱动的局部增强方法以实现内容感知的局部增强，该方法通过让众包工作者对图像编辑功能的参数进行局部优化来达成目标。为了简化局部参数优化的过程，我们提出了一种基于主动学习的局部滤波器。仅需确定由主动学习方法选出的少数关键像素处的参数，其余像素的参数可通过回归模型自动预测；所选关键像素处的参数可独立优化，将优化问题拆解为一系列单滑块调整任务。实验结果表明，我们提出的滤波器性能优于现有滤波器，且我们的增强结果在视觉上比现有增强方法的结果更具美感。我们的源代码和结果可在https://github.com/satoshi-kosugi/crowd-powered获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
