Toronto Metropolitan University
Browse

Large receptive field networks for accurate high-scale image super-resolution

Download (13.89 MB)
thesis
posted on 2021-05-23, 18:12 authored by George Seif
This thesis presents a novel convolutional neural network architecture for high-scale image super-resolution. In particular, we introduce two separate modifications that can be made to the convolutional layers in the network: one-dimensional kernels and dilated kernels. We show how both of these methods can be used to expand the receptive field and performance of super-resolution networks, without increasing the number of trainable parameters or network depth. We show that these modifications can easily be integrated into any convolutional neural network to improve performance. Our methods are especially effective for the challenging high scale super-resolution due to the expanded network receptive field. We conduct extensive empirical evaluations to demonstrate the effectiveness of our methods, showing strong improvements over the state-of-the-art.

History

Language

English

Degree

  • Master of Applied Science

Program

  • Electrical and Computer Engineering

Granting Institution

Ryerson University

LAC Thesis Type

  • Thesis

Year

2018

Usage metrics

    Electrical and Computer Engineering (Theses)

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC