تصفح حسب المؤلف "K�ranyaz, Serkan"
-
SELF-ORGANIZED RESIDUAL BLOCKS FOR IMAGE SUPER-RESOLUTION
Keleş, Onur; Tekalp, A. Murat; Malik, Junaid; Kιranyaz, Serkan ( IEEE Computer Society , 2021 , Conference Paper)It has become a standard practice to use the convolutional networks (ConvNet) with RELU non-linearity in image restoration and super-resolution (SR). Although the universal approximation theorem states that a multi-layer ... -
SELF-ORGANIZED VARIATIONAL AUTOENCODERS (SELF-VAE) FOR LEARNED IMAGE COMPRESSION
Yílmaz, M. Akín; Kelesş, Onur; Güven, Hilal; Tekalp, A. Murat; Malik, Junaid; Kíranyaz, Serkan... more authors ... less authors ( IEEE Computer Society , 2021 , Conference Paper)In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space. Recently, ...