viernes, 10 de febrero de 2017

Pixel Recursive Super Resolution. Paper @Google Brain. Ryan Dahl, Mohammad Norouzi & Jonathon Shlens

Como continuación a los posts últimos sobre papers del miércoles, 11 de enero de 2017 Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation y del domingo, 8 de enero de 2017 "Learning from Simulated and Unsupervised Images through Adversarial Training" . @apple inc. Research ... hoy traemos a este espacio otro paper de Google ... aquí os dejamos el

We present a pixel recursive super resolution model that
synthesizes realistic details into images while enhancing
their resolution. A low resolution image may correspond
to multiple plausible high resolution images, thus modeling
the super resolution process with a pixel independent conditional
model often results in averaging different details–hence blurry edges. By contrast, our model is able to represent a multimodal conditional distribution by properly modeling the statistical dependencies among the high resolution image pixels, conditioned on a low resolution input. We employ a PixelCNN architecture to define a strong prior over natural images and jointly optimize this prior with a deep conditioning convolutional network. Human evaluations indicate that samples from our proposed model look.(leer más...)

 Fuente: [slideshare vía google ]