基于语义相似性传播的图像彩色化  

Image colorization via semantic similarity propagation

作　　者：孟思弘 刘浩 方昊天 僧冰枫 杜正君 MENG Sihong;LIU Hao;FANG Haotian;SENG Bingfeng;DU Zhengjun(School of Computer Technology and Application,Qinghai University,Xining Qinghai 810016,China;Intelligent Computing and Application Laboratory of Qinghai Province,Xining Qinghai 810016,China)

机构地区：[1]青海大学计算机技术与应用学院,青海西宁810016 [2]青海省智能计算与应用实验室,青海西宁810016

出　　处：《图学学报》2025年第1期126-138,共13页Journal of Graphics

基　　金：青海省自然科学基金青年项目(2023-ZJ-951Q)。

摘　　要：图像彩色化旨在将灰度图像转换为彩色图像,这一技术在计算机图形学和计算机视觉领域内长期受到研究者们的广泛关注,并在图像复原、医学成像、电影修复、艺术创作等诸多领域广泛应用,在实际应用中展现出巨大的潜力。经过数十年的发展,研究者们提出了大量基于交互、基于规则以及基于深度学习的算法来提升图像彩色化的效果。尽管如此,现有的图像彩色化算法仍然存在一些显著的缺陷,如计算效率偏低、交互繁琐、颜色饱和度偏低以及无法避免颜色溢出现象等问题。针对上述问题,提出了一种基于语义相似性传播的图像彩色化算法。算法首先利用深度神经网络提取输入灰度图像的语义特征,并构建特征空间。然后,将图像彩色化问题形式化为一个高效的、基于语义相似性传播的能量优化问题,通过优化能量函数求解灰度图像的色度值,从而将用户提供的笔触颜色传播到图像的其他区域。此外,还采用了三线性插值的方法加速能量优化和颜色传播,大幅提升了计算效率。为了验证算法的有效性,在收集的图像集上从多个角度进行了实验评估,包括图像视觉效果、生成图像的质量、算法的运行时间,以及用户交互体验。大量定性和定量实验结果表明,该算法在更少的用户交互下实现了更准确、高效、自然的彩色化效果。Image colorization aims to convert grayscale images into color images,a technique that has long received extensive attention from researchers in the fields of computer graphics and computer vision.It has found wide applications in areas such as image restoration,medical imaging,film restoration,and artistic creation.Over decades of development,researchers have proposed a large number of interaction-based,rule-based,and deep learning-based algorithms to enhance the colorization effect of images.Nevertheless,the existing image colorization algorithms exhibit some significant shortcomings,such as low computational efficiency,cumbersome user interaction,low color saturation,and the occurrence of color overflow.To address these challenges,an image colorization algorithm based on semantic similarity propagation was proposed.Semantic features of the input grayscale image were extracted using deep neural networks,and a feature space was constructed.Then,the image colorization task was formalized as an efficient energy optimization problem based on semantic similarity propagation,enabling the propagation of user-supplied stroke colors to other regions of the image.In addition,a trilinear interpolation method was employed to accelerate both energy optimization and color propagation,significantly enhancing computational efficiency.In order to verify the effectiveness of the algorithm,experiments were conducted on a collected image set,evaluating multiple dimensions,such as image visual effect,generated image quality,algorithm running time,and user interaction experience.The results of a large number of qualitative and quantitative experiments demonstrated that the proposed algorithm achieved more accurate,efficient,and natural colorization with reduced user interaction requirements,while achieving substantial improvements in computational efficiency.

关 键 词：图像彩色化 交互式 语义相似性 传播 能量优化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]