用于阴影去除的小波非均匀扩散模型  

Shadow removal with wavelet-based non-uniform diffusion model

作　　者：黄颖[1,2] 程彬 房少杰 刘歆[2] Huang Ying;Cheng Bin;Fang Shaojie;Liu Xin(School of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Software Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065 [2]重庆邮电大学软件工程学院,重庆400065

出　　处：《中国图象图形学报》2025年第1期66-82,共17页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62471076)。

摘　　要：目的现有的阴影去除方法通常依赖于像素级重建,旨在学习阴影图像和无阴影图像之间的确定性映射关系。然而阴影去除关注阴影区域的局部恢复,容易导致在去除阴影的同时破坏非阴影区域。此外,现有的大多数扩散模型在恢复图像时存在耗时过长和对分辨率敏感等问题。为此,提出了一种用于阴影去除的小波非均匀扩散模型。方法首先将图像通过小波分解为低频分量与高频分量,然后针对低频和高频分量分别设计扩散生成网络来重建无阴影图像的小波域分布,并分别恢复这些分量中的各种退化信息,如低频(颜色、亮度)和高频细节等。结果实验在3个阴影数据集上进行训练和测试,在SRD(shadow removal dataset)数据集中,与9种代表性方法进行比较,在非阴影区域和整幅图像上,峰值信噪比(peak signal-to-noise ratio,PSNR)、结构相似性(structural similarity index,SSIM)和均方根误差(root mean square error,RMSE)均取得最优或次优的结果;在ISTD+(augmented dataset with image shadow triplets)数据集中,与6种代表性方法进行比较,在非阴影区域上,性能取得了最佳,PSNR和RMSE分别提高了0.47 dB和0.1。除此之外,在SRD数据集上,ShadowDiffusion方法在生成不同分辨率图像时性能有明显差异,而本文方法性能基本保持稳定。此外,本文方法生成速度与其相比提高了约4倍。结论提出的方法能够加快扩散模型的采样速度,在去除阴影的同时,恢复出阴影区域缺失的颜色、亮度和丰富的细节等信息。Objective Shadows are a common occurrence in optical images captured under partial or complete obstruction of light.In such images,shadow regions typically exhibit various forms of degradation,such as low contrast,color distor⁃tion,and loss of scene structure.Shadows not only impact the visual perception of humans but also impose constraints on the implementation of numerous sophisticated computer vision algorithms.Shadow removal can assist in many computer vision tasks.It aims to enhance the visibility of shadow regions in images and achieve consistent illumination distribution between shadow and non-shadow regions.Currently,deep learning-based shadow removal methods can be roughly divided into two categories.One typically utilizes deep learning to minimize the pixel-level differences between shadow regions and their corresponding non-shadow regions,aiming to learn deterministic mapping relationships between shadow and nonshadow images.However,the primary focus of shadow removal lies in locally restoring shadow regions,often overlooking the essential constraints required for effectively restoring boundaries between shadow and non-shadow regions.As a result,discrepancies in brightness exist between the restored shadow and non-shadow areas,along with the emergence of artifacts along the boundaries.Another approach involves using image generation models to directly model the complex distribution of shadow-free images,avoiding the direct learning of pixel-level mapping relationships,and treating shadow removal as a conditional generation task.While diffusion models have garnered significant attention due to their powerful generation capabilities,most existing diffusion generation models suffer from issues such as time-consuming image restoration and sen⁃sitivity to resolution when recovering images.Inspired by these challenges,a wavelet non-uniform diffusion model(WNDM)is proposed,which combines the advantages of wavelet decomposition and the generation ability of diffusion mod⁃els to solve the above problems.

关 键 词：阴影去除 扩散模型(DM) 小波变换 双分支网络 噪声调度表 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]