Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
share
In "extreme" computational imaging that collects extremely undersampled or noisy measurements, obtaining an accurate image within a reasonable computing time is challenging. Incorporating image mapping convolutional neural networks (CNN) to iterative image recovery has great potential to resolve this issue. This paper 1) incorporates image mapping CNN using identical convolutional kernels in both encoders and decoders into block coordinate descent (BCD) optimization method -- referred to BCD-Net using identical encoding-decoding CNN structures -- and 2) applies alternating direction method of multipliers to train the proposed BCD-Net. Numerical experiments show that, for a) denoising moderately low signal-to-noise-ratio images and b) extremely undersampled magnetic resonance imaging, the proposed BCD-Net achieves (significantly) more accurate image recovery, compared to BCD-Net using distinct encoding-decoding structures and/or the conventional image recovery model using both wavelets and total variation.
READ FULL TEXT