arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.08080cs.CV
收藏

基于神经网络的图像序列修图颜色算子

Neural Color Operators for Sequential Image Retouching

Tsinghua University(清华大学);Baidu Inc.(百度公司)

Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding

摘要:

我们提出了一种新的图像修图方法,通过建模的修图过程中执行一系列新引入的可训练的神经颜色算子。神经颜色算子模仿传统颜色算子的行为,并学习逐像素的颜色变换,而其强度由标量控制。为了反映颜色算子的同态性质,我们采用等变映射并采用编码器-解码器结构,该结构将非线性颜色变换映射到更简单的变换(即,在高维空间中的平移。通过分析全局图像统计,使用基于CNN的强度预测器来预测每个神经颜色算子的标量强度。总的来说,我们的方法是相当轻量级的,并提供灵活的控制。在公共数据集上的实验和用户研究表明,与SOTA方法相比,我们的方法在定量测量和视觉质量方面都取得了最好的结果。代码和预训练模型可在https://github.com/amberwangyili/neurop上找到

英文摘要:

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

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。

↑