Algorithm 1: Compressed Poisson noise reduction based on the SCENet

Input: degraded image z and trained parameters aL=1,...,20, F=1,2,3, bL=1,...,20

Output: restored image y

1:  Compute DC, AC(1,0), AC(0,1) by T{z}.

2:  Obtain S = {SDC, SAC(1,0), SAC(0,1)} by merging the each coefficient.

3:  for L = 1, …, 20 do

4:  Stabilize using VST by f{S}.

5:  Apply convolution with trained parameters and then destabilize it by f −1{aL,F* f{S}}.

6:  Appy BN and ReLU by max(BN{f −1{aL,F* f{S}}}, 0).

7:  end for

8:  Obtain Sout = {SDC,out, SAC(1,0),out, SAC(0,1),out} by applying a fully-connected layer.

9:  Estimate Lout by T−1{Sout}.

10: Obtain H by z −T−1{S}.

11: Estimate Hout by running steps 3−8 above with H and bL=1,...,20 instead of S and aL,F.

12: Estimate final restored image by y = Lout + Hout.