Skip to main content
. 2020 Jan 22;19(4):351–358. doi: 10.2463/mrms.mp.2019-0106

Fig. 1.

Fig. 1

Architecture of the 3D convolutional ladder network. The first line is the “corrupted encoder”, the second line is the decoder, and the third line is the “clean encoder”. Each arrow in the encoder/decoder consists of 3 × 3 × 3 convolution/deconvolution with stride 2, batch normalization, and an exponential linear unit. g: de-noising function, Cd: cost function, N[0, σ2]: random sample from normal distribution with mean = 0 and variance = σ2.