Algorithm 1 Disparity maps fusion algorithm

Input:k disparity maps $D_k$, k reliability masks $m_k$, and k baselines $b_k$ Output: disparity map $D_{\mathrm{msm}}$ 1:baseline = 4 2:while baseline > 0 and not all pixels filled in do 3: for all pixels $(i,j)$ in $D_{\mathrm{msm}}$ not yet filled in do 4:  create empty vector K of estimations to consider 5:  for all k do 6:   if $b_k$ == baseline and $m_k(i,j)==1$ then 7:    add $D_k$ to vector K 8:   end if 9:  end for 10:  $D_{\mathrm{msm}}(i,j)$ = weighted_mean($K,i,j$) 11: end for 12: baseline = baseline − 1 13:end while