English

Convolutional Networks with MuxOut Layers as Multi-rate Systems for Image Upscaling

Computer Vision and Pattern Recognition 2017-05-23 v1

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T19:54:49.239Z