The main question we try to answer in this work is whether it is feasible to employ super-resolution (SR) algorithms to increase the spatial resolution of endoscopic high-definition (HD) images in order to reveal new details which may have got lost due to the limited endoscope magnification of the HD endoscope used (e.g. mucosal structures).
For this purpose we compare the quality achieved of different SR methods. This is done on standard test images as well as on images obtained from endoscopic video frames. We also investigate whether compression artifacts have a noticeable effect on the SR results.
We show that, due to several limitations in case of endoscopic videos, we are not consistently able to achieve a higher visual quality when using SR algorithms instead of bicubic interpolation.