Disparity map quality assessment is crucial to evaluate the accuracies of stereo matching algorithms. Several widely used measures such as root mean square (RMS), mean absolute error (MAE) and bad matching pixels (BMP) have been proposed to evaluate the similarity between disparity map and ground truth (GT) map. These measures are based on grey-scale errors while ignoring the structural similarity between disparity map and GT. In this paper, we propose a united similarity measure based on sructure similarity and normalized RMS (USNR) for disparity map quality assessment. Our new measure is able to simultaneously evaluate grey-scale similarity and region-aware structural similarity between disparity map and GT map. Experiments have been carried out using stereo pair datasets from various scenes, including street view, planetary, natural landscape and urban, to demonstrate the feasibility, reliability and robustness of our measure compared to state-of-the-art evaluation methods.

视差图质量评估对于评估立体声匹配算法的准确性至关重要。已经提出了几种广泛使用的度量，例如均方根（RMS），平均绝对误差（MAE）和不良匹配像素（BMP），以评估视差图和地面真实（GT）图之间的相似性。这些措施基于灰度误差，而忽略了视差图和GT之间的结构相似性。在本文中，我们提出了一种基于结构相似度和归一化RMS（USNR）的统一相似度度量，用于视差图质量评估。我们的新措施能够同时评估视差图和GT图之间的灰度相似度和区域感知的结构相似度。实验使用的是来自各种场景的立体对数据集，包括街景，行星，