标题: 【SIGGRAPH Asia 2012专题*技术论文】材料和图像：在图形文物评价中不合格图像质量指标的新测量结果显示 [打印本页] 作者: . 时间: 2012-12-19 15:53 标题: 【SIGGRAPH Asia 2012专题*技术论文】材料和图像：在图形文物评价中不合格图像质量指标的新测量结果显示 【SIGGRAPH Asia 2012专题*技术论文】
材料和图像：在图形文物评价中不合格图像质量指标的新测量结果显示
New Measurements Reveal Weaknesses of Image Quality Metrics in Evaluating Graphics Artifacts
Martin Čadik, Robert Herzog, Rafal Mantiuk, Karol Myszkowski, Hans-Peter Seidel
摘要：可靠的检测全局照明和渲染文物形式的局部失真地图是非常重要的许多图形应用。虽然许多质量指标已制定的这一任务，他们经常调整压缩/传输文物和尚未评估范围内的综合cg-images。在这项工作中，我们实验在观察员使用***sh-painting接口直接标记图像区域有明显的/令人反感的扭曲的存在/没有一个高质量的参考图像，分别。所收集的数据表明较高的相关性之间的with-reference观察员和无参考标记。同时，我们要求perpixel图像质量数据揭示弱点既简单（信噪比，均方误差，scie-lab）和晚期（独运，ms-ssim，hdr-vdp-2）质量指标。最成问题的是过度敏感的亮度和对比度的变化，校准近visibility-threshold扭曲，缺乏之间的歧视似是而非/难以置信的照明，和穷人的空间定位的扭曲，多尺度的度量。我们相信，我们的数据有可能进一步改善现有的质量指标，同时也分析了显着的扭曲和渲染，我们调查视觉等价与和无参考资料。
Abstract：Reliable detection of global illumination and rendering artifacts in the form of localized distortion maps is important for many graphics applications. Although many quality metrics have been developed for this task, they are often tuned for compression/transmission artifacts and have not been evaluated in the context of synthetic CG-images. In this work, we ***n two experiments where observers use a ***sh-painting interface to directly mark image regions with noticeable/objectionable distortions in the presence/absence of a high-quality reference image, respectively. The collected data shows a relatively high correlation between the with-reference and no-reference observer markings. Also, our demanding perpixel image-quality datasets reveal weaknesses of both simple (PSNR, MSE, sCIE-Lab) and advanced (SSIM, MS-SSIM, HDR-VDP-2) quality metrics. The most problematic are excessive sensitivity to brightness and contrast changes, the calibration for near visibility-threshold distortions, lack of discrimination between plausible/implausible illumination, and poor spatial localization of distortions for multi-scale metrics. We believe that our datasets have further potential in improving existing quality metrics, but also in analyzing the saliency of rendering distortions, and investigating visual equivalence given our with- and no-reference data.
