We interpret convolutional networks as adaptive filters and combine them with so-called MuxOut layers to efficiently upscale low resolution images. We formalize this interpretation by deriving a linear and space-variant structure of a convolutional network when its activations are fixed. We introduce general purpose algorithms to analyze a network and show its overall filter effect for each given location. We use this analysis to evaluate two types of image upscalers: deterministic upscalers that target the recovery of details from original content; and second, a new generation of upscalers that can sample the distribution of upscale aliases (images that share the same downscale version) that look like real content.
@article{arxiv.1705.07772,
title = {Convolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling},
author = {Pablo Navarrete Michelini and Hanwen Liu},
journal= {arXiv preprint arXiv:1705.07772},
year = {2017}
}