论文标题
神经颜色操作员用于顺序图像修饰
Neural Color Operators for Sequential Image Retouching
论文作者
论文摘要
我们通过对修饰过程进行建模来提出一种新型的图像修饰方法，以执行一系列新引入的可训练的神经色运算符。神经颜色操作员模仿了传统颜色运算符的行为，并在其强度由标量控制的同时学习了Pixelwise Color Transformation。为了反映颜色运算符的同态特性，我们采用了模棱两可的映射，并采用编码器编码器结构，该结构将非线性颜色转换映射到高维空间中的更简单的转换（即翻译）。通过分析全球图像统计数据，使用基于CNN的强度预测指标预测每个神经颜色算子的标量强度。总体而言，我们的方法相当轻巧，并提供灵活的控件。公共数据集的实验和用户研究表明，与SOTA方法相比，我们的方法始终取得了最佳结果。代码和预估计的模型可在https://github.com/amberwangyili/neurop上提供
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. The code and pretrained models are provided at https://github.com/amberwangyili/neurop
