Using full reference image quality metrics to detect game engine artefacts

Contemporary game engines offer an outstanding graphics quality but they are not free from visual artefacts. A typical example is aliasing, which, despite advanced antialiasing techniques, is still visible to the game players. Essential deteriorations are the shadow acne and peter panning artefacts related to deficiency of the shadow mapping technique. Also Z-fighting, caused by the incorrect order of drawing polygons, significantly affects the quality of the graphics and makes the gameplay difficult. These artefacts are laborious to eliminate in an algorithm way because either they require computational effort inadequate to obtained results or visibility of artefacts depends on the ambiguous parameters. In this work we propose a technique, in which visibility of deteriorations is perceptually assessed by human observers. We conduct subjective experiments in which people manually mark the visible local artefacts in the screenshots from the games. Then, the detection maps averaged over a number of observers are compared with results generated by the image quality metrics (IQMs). Simple mathematically-based metric - MSE, and advanced IQMs: S-CIELAB, SSIM, MSSIM, and HDR-VDP-2 are evaluated. We compare convergence in the detection between the maps created by humans and computed by IQMs. The obtained results show that SSIM and MSSIM metrics outperform other techniques. However, the results are not indisputable because, for small and scattered aliasing artefacts, HDR-VDP-2 metrics reports the results most consistent with the average human observer. Notwithstanding, the results suggest that it is feasible to use the IQMs detection maps to leverage and calibrate the rendering algorithms directly based on the analysis of quality of the output images.