Skip to main content

Advertisement

Table 2 Performance evaluation using different prior terms E P (d) with proposed E D (d). The errors are shown in terms of bad matching pixels and these are computed over the whole image with δ=1

From: A learned sparseness and IGMRF-based regularization framework for dense disparity estimation using unsupervised feature learning

E P (d) Venus Teddy Cones
Truncated quadratic 1.95 15.38 11.62
Truncated linear 0.91 12.86 10.96
Potts 1.11 13.93 11.01
E IGMRF(d) 0.40 11.41 9.64
E IGMRF(d) + E sparse(d) using DCT 0.38 11.1 9.36
E IGMRF(d) + E sparse(d) using K-SVD 0.30 10.60 9.12
E IGMRF(d) + E sparse(d) using autoencoder 0.20 9.76 8.46