The quality of each restored image in you subission will be ranked as follows:
$$p_i= PSNR (\textrm{restored}_i, \textrm{original}_i) \in [0, +\infty]$$
$$s_i =SSIM (\textrm{restored}_i, \textrm{original}_i) \in [0,1]$$
The submission score is computed  as the average product of both metrics
$$score = \frac{1}{N} \sum_i s_i p_i $$ 
A perfectly recovered image is expected to get 
$$s_i \approx 1 $$ 
 $$p_i > 20 \ \textrm{dB}$$