DeepLPF: Deep Local Parametric Filters for Image Enhancement
DeepLPF: Deep Local Parametric Filters for Image Enhancement
复制标题
DOI：
10.1109/cvpr42600.2020.01284
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
S. Moran;Pierre Marza;Steven G. McDonagh;Sarah Parisot;G. Slabaugh
中科院分区：
文献类型：
--
作者：
S. Moran;Pierre Marza;Steven G. McDonagh;Sarah Parisot;G. Slabaugh
数字艺术家经常通过手动润色来提高数字照片的美学质量。除了全球调整外，专业的图像编辑程序还提供针对图像特定部分的本地调整工具。选项包括参数(分级、径向滤镜)和不受约束的画笔工具。这些极富表现力的工具可实现各种本地图像增强。然而，它们的使用可能会很耗时，而且需要艺术能力。最先进的自动图像增强方法通常专注于学习像素级或全局增强。前者可能噪音大且缺乏可解释性，而后者可能无法捕捉到细粒度的调整。在本文中，我们介绍了一种新的方法，使用三种不同类型的学习的空间局部滤波器(椭圆滤波器，分级滤波器，多项式滤波器)来自动增强图像。我们介绍了一种深度神经网络，称为深度局部参数滤波器(DeepLPF)，它回归这些空间局部化滤波器的参数，然后自动应用这些参数来增强图像。DeepLPF提供了一种自然形式的模型正则化，并支持可解释的、直观的调整，从而产生视觉上令人满意的结果。我们报告了多个基准测试，并显示DeepLPF在MIT-Adobe 5k数据集的两个变体上产生了最先进的性能，通常使用的参数只是竞争方法所需的一小部分。
Digital artists often improve the aesthetic quality of digital photographs through manual retouching. Beyond global adjustments, professional image editing programs provide local adjustment tools operating on specific parts of an image. Options include parametric (graduated, radial filters) and unconstrained brush tools. These highly expressive tools enable a diverse set of local image enhancements. However, their use can be time consuming, and requires artistic capability. State-of-the-art automated image enhancement approaches typically focus on learning pixel-level or global enhancements. The former can be noisy and lack interpretability, while the latter can fail to capture fine-grained adjustments. In this paper, we introduce a novel approach to automatically enhance images using learned spatially local filters of three different types (Elliptical Filter, Graduated Filter, Polynomial Filter). We introduce a deep neural network, dubbed Deep Local Parametric Filters (DeepLPF), which regresses the parameters of these spatially localized filters that are then automatically applied to enhance the image. DeepLPF provides a natural form of model regularization and enables interpretable, intuitive adjustments that lead to visually pleasing results. We report on multiple benchmarks and show that DeepLPF produces state-of-the-art performance on two variants of the MIT-Adobe 5k dataset, often using a fraction of the parameters required for competing methods.