by V. Bruni, D.De Canditiis and D. Vitulano
Because of masking , any kind of degradation on video sequences is not perceived in the same way in the whole image.
For instance, noise is:
Two examples are shown in the Figures below:
On the other hand, motion is not perceived in the same way in the whole sequence. It is:
A perception-based block classification can be then used:
1-st Class: flat blocks - only denoising si required
2-nd Class: edge blocks - motion estimation and denoising are required
3-rd Class: textured blocks - no operations are required.
A block scheme of the aforementioned classification is shown below:
Starting from the classical SSIM [1,2]:
one can get the two following hypothesis tests:
Apart from their simplicity, a confidence level can be proven for them as well as a very low complexity:
operations per pixel, where N is the total number of pixels in the block B , while k is the number of its sub-blocks.
Complexity can be further improved via a more effective version of SUVEHP: Fast SUVEHP (see  for details), that has the following complexity:
Below there are three examples that show that the proposed classification though simple is still effective:
|Classification map. Class 1,2 and 3 respectively are white, gray and black.||Classification map.||Classification map.|
The subjective quality of the restored sequences is unchanged or sometimes better with a considerable computational effort saving.