Subjective evaluation of single-frame superresolution algorithms

We comparatively evaluate several single-frame interpolation methods with respect to a reference multi-frame superresolution algorithm. The objective performance was measured using Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), while subjective evaluation was based on two-alternative forced choice scores. Rank correlation was used to assess the degree of agreement between subjective and objective measures, and to determine the best performing single-frame interpolation method to be used in video industry.