@InProceedings{NepomucenoSilv:2021:EvLoFu,
author = "Nepomuceno, Raphael and Silva, Michel M.",
affiliation = "{Universidade Federal de Vi{\c{c}}osa} and {Universidade Federal
de Vi{\c{c}}osa}",
title = "Evaluating Loss Functions for Illustration Super-Resolution Neural
Networks",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
address = "Porto Alegre",
keywords = "super-resolution,convolutional neural networks,deep
learning,computer vision.",
abstract = "As display technologies evolve and high-resolution screens become
more available, the desirability of images and videos with high
perceptual quality grows in order to properly utilize such
advances. At the same time, the market for illustrated mediums,
such animations and comics, has been in steady growth over the
past years. Based on these observations, we were motivated to
explore the super-resolution task in the niche of drawings. In
absence of original high-resolution imagery, it is necessary to
use approximate methods, such as interpolation algorithms, to
enhance low-resolution media. Such methods, however, can produce
undesirable artifacts in the reconstruct images, such as blurring
and edge distortions. Recent works have successfully applied deep
learning to this task, but such efforts are often aimed at
real-world images and do not take in account the specifics of
illustrations, which emphasize lines and employ simplified
patterns rather than complex textures, which in turn makes visual
artifacts introduced by algorithms easier to spot. With these
differences in mind, we evaluated the effects of the choice of
loss functions in order to obtain accurate and perceptually
pleasing results in the super-resolution task for comics,
cartoons, and other illustrations. Experimental evaluations have
shown that a loss function based on edge detection performs best
in this context among the evaluated functions, though still
showing room for further improvements.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
language = "en",
ibi = "8JMKD3MGPEW34M/45E82PS",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45E82PS",
targetfile = "paper.pdf",
urlaccessdate = "2024, Apr. 29"
}