视觉显著性驱动的全景渲染图非局部降噪  

Visual saliency-driven non-local denoising of rendered panoramic images

作　　者：韩鲁光 陈纯毅[1] 申忠业 胡小娟[1] 于海洋[1] Han Luguang;Chen Chunyi;Shen Zhongye;Hu Xiaojuan;Yu Haiyang(School of Computer Science and Technology,Changchun University of Science and Technology,Changchun 130022,China)

机构地区：[1]长春理工大学计算机科学技术学院,长春130022

出　　处：《中国图象图形学报》2024年第4期939-952,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(U19A2063);吉林省科技发展计划项目(20230201080GX)。

摘　　要：目的传统降噪方法通常忽视人眼感知因素,对不同区域的图像块都进行同等处理。当使用传统降噪算法对全景画面滤波处理时,全景画面两极区域容易产生模糊问题,尤其是通过视口观察时,该问题更加明显。针对此问题,提出一种视觉显著性驱动的蒙特卡洛渲染生成全景图非局部均值(visual saliency driven non-local means,VSD-NLM)滤波降噪算法。方法在VSD-NLM算法中首先使用全景图显著区域检测算法获取全景画面的显著区域;然后使用梯度幅值相似性偏差辅助的非局部均值(gradient magnitude similarity deviation assisted non-local means,GMSDA-NLM)滤波算法,降低显著区域的噪声;同时设计并行非局部均值(parallel non-local means,P-NLM)滤波算法,加快降噪处理速度,降低非显著区域噪声;最后利用改进的Canny算法提取梯度特征,同时结合各向异性扩散引导滤波来优化降噪结果。结果采用结构相似度(structural similarity,SSIM)和FLIP作为评价指标,来对比VSDNLM算法与非局部均值滤波算法、多特征非局部均值滤波算法以及渐进式去噪算法等其他算法的性能。实验结果表明,VSD-NLM算法的降噪结果在客观评价指标上均优于对比算法,SSIM值比其他算法平均提高14.7%,FLIP值比其他算法平均降低15.2%。在视觉效果方面,VSD-NLM算法能够减轻全景画面模糊,提升视觉感知质量。本文对GMSDA-NLM和P-NLM算法的有效性进行了实验验证,相较于非局部均值滤波算法,GMSDA-NLM算法能够有效去除噪声并保持图像细节的完整性。P-NLM算法在运行速度方面相较对比算法平均提高约6倍,与串行算法生成的图像之间的SSIM值可达到0.996。结论本文算法能够更好地用于全景图降噪,滤波效果更佳,对全景电影制作应用有重要的理论和实际意义。Objective Panoramic movie technology has experienced notable advancements to enrich the audiovisual experience for viewers,resulting in a heightened sense of immersion within the visual environment.Nevertheless,the production of high-quality images poses a challenge for conventional rasterization techniques,necessitating the exploration of alternative approaches.Monte Carlo path tracing algorithms have been proven effective in generating high-quality images,offering exceptional visual fidelity in various rendering applications.However,the computational overhead associated with this algorithm remains challenging.Thus,reducing the number of pixels sampled in Monte Carlo path tracing is a common approach to optimize computation.However,this reduction often introduces noticeable noise in the resulting images,compromising their overall quality.This paper aims to address the issue of image noise in Monte Carlo path tracing by exploring and proposing advanced techniques for denoising.Two main denoising approaches are commonly used in the domain of Monte Carlo rendering.The first approach utilizes traditional filtering methods with artificially designed filters to remove image noise.This approach is versatile,but its effectiveness in noise removal may be limited,often resulting in residual noise.The second approach involves deep learning-based denoising methods,which can effectively eliminate noise but may exhibit performance limitations on specific image types.Most existing image denoising algorithms are currently developed and studied for ordinary flat images,with limited research dedicated to denoising algorithms specifically designed for panoramic images.Panoramic images possess unique characteristics,including a 360°field of view in the horizontal direction,a 18o°field of view in the vertical direction,distorted edges,and varying prominence of equatorial and polar pixels as perceived by human observers.Conventional flat image denoising methods often fail to fully account for these panoramic image characteristics,l

关 键 词：全景图像 非局部均值滤波 梯度幅值相似性偏差(GMSD) 引导滤波 图像降噪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]