1.6k citations · 12.4k across the 394 of their papers we have counts for
3 papers · 2 filters
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Mehdi S. M. Sajjadi, Bernhard Schölkopf, Michael Hirsch
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is mea…
Depth Estimation Through a Generative Model of Light Field Synthesis
Mehdi S. M. Sajjadi, Rolf Köhler, Bernhard Schölkopf +1
Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such en…
End-to-End Learning for Image Burst Deblurring
Patrick Wieschollek, Bernhard Schölkopf, Hendrik P. A. Lensch +1
We present a neural network model approach for multi-frame blind deconvolution. The discriminative approach adopts and combines two recent techniques for image deblurring into a si…