Our super resolution implementation internally upscales video 2 times. If you ask Video Enhancer or Super Resolution plugin to upsize video 4 times using one instance of SR, it will upsize it 2x with super resolution approach and then 2x more using just a high quality image resampling method. For this reason we usually recommended to make a chain of 2 SR instances, each upsizing 2 times. This is what we did in our comparison. But are two instances really required?

To answer this question we took 10 videos from the comparison and upsized them 4 times using just one instance of SR. Here are the results in terms of PSNR:

It turned out the PSNR values for one instance were just 0.09 dB lower in average than for two instances. Some videos, like sw.avi and alice.avi were originally quite smooth and had not so much high frequency details due to their computer-generated content and compression. For these videos PSNR difference between one and two passes of super resolution was minimal - just 0.06 dB. And for bjorn.avi, where we had a high-bitrate high resolution original with lots of details, the difference between one and two passes was maximal - 0.17 dB. But anyway it's hardly noticeable comparing to other video resizing methods, as you can see from the chart.

tags: super_resolution