Perceptual Autoencoder for Compressive Sensing Image Reconstruction (CROSBI ID 279843)
Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Ralašić, Ivan ; Seršić, Damir ; Šegvić, Siniša
engleski
Perceptual Autoencoder for Compressive Sensing Image Reconstruction
This paper presents a non-iterative deep learning approach to compressive sensing (CS) image reconstruction using a convolutional autoencoder and a residual learning network. An efficient measurement design is proposed in order to enable training of the compressive sensing models on normalized and mean-centred measurements, along with a practical network initialization method based on principal component analysis (PCA). Finally, perceptual residual learning is proposed in order to obtain semantically informative image reconstructions along with high pixel-wise reconstruction accuracy at low measurement rates.
compressive sensing ; convolutional autoencoder ; deep learning ; image reconstruction ; perceptual loss ; principal component analysis
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano