Ssim Based Range Image Quality Assessment

Although image quality assessment (IQA) has observed much research and advancement in the past, not much progress has been made towards the development of quality assessment metrics for range images. The current metrics being used to assess the quality of range images are reminiscent to the old IQA metrics such as mean squared error that have since been replaced with metrics which better correlate with human perception. This paper presents two new algorithms for range image quality assessment (RIQA). The first, R-SSIM, is based off the Multi-Scale Structural Similarity Index (MS-SSIM), while the other is an extension of the Complex Wavelet SSIM (CW-SSIM) metric for use in RIQA. The utility of these metrics is demonstrated through a re-evaluation of Scharstein and Szeliski’s online evaluation of dense two-frame stereo correspondence algorithms.