There have been some changes to the algorithm though, although the general idea has remained more or less the same. The steps now look more like the following:
- Calculate an initial guess (using a different upscaler)
- Downscale and calculate differences with original image.
- Scale those differences to the final size
- Improve guess by:
- Softening the image
- Subtracting differences with the original image
- Sharpening (optional)
- Removing aliasing (optional)
- Removing ringing (optional)
- Repeat steps 2-4 several times.