Image quality assessment: Difference between revisions

Line 18: Line 18:
==Spherical Quality Assessment==
==Spherical Quality Assessment==


* Yu ''et al.''<ref name="yu2015framework></ref> propose Spherical PSNR (SPSNR) and WSPSNR.
* WS-PSNR is a standard PSNR calculation where the mean squared error is weighted by the size of each pixel.
<math>
\begin{align}
WMSE &= \frac{1}{\sum_{i,j}w(i,j)} \sum_{i,j} (I_1(i,j)-I_2(i,j))^2 * w(i,j)\\
WS\_PSNR &= 10\log_{10}(\frac{R^2}{WMSE})\\
\end{align}
</math>
* Yu ''et al.''<ref name="yu2015framework></ref> propose Spherical PSNR (S-PSNR). In S-PSNR, points are randomly sampled on a sphere and back projected to the reference and reconstructed images. In practice, these randomly sampled points need to be saved for reproducibility. They use 655262 points which are available [https://github.com/mattcyu1/omnieval/blob/master/compsph/sphere_655362.txt on their repo].


==References==
==References==