Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update2021: (UTC)
Metadata Last Update2021: (UTC) administrator
Citation KeyNepomucenoSilv:2021:EvLoFu
TitleEvaluating Loss Functions for Illustration Super-Resolution Neural Networks
Access Date2022, Jan. 21
Number of Files1
Size8458 KiB
Context area
Author1 Nepomuceno, Raphael
2 Silva, Michel M.
Affiliation1 Universidade Federal de Viçosa
2 Universidade Federal de Viçosa
EditorPaiva, Afonso
Menotti, David
Baranoski, Gladimir V. G.
Proença, Hugo Pedro
Junior, Antonio Lopes Apolinario
Papa, João Paulo
Pagliosa, Paulo
dos Santos, Thiago Oliveira
e Sá, Asla Medeiros
da Silveira, Thiago Lopes Trugillo
Brazil, Emilio Vital
Ponti, Moacir A.
Fernandes, Leandro A. F.
Avila, Sandra
Conference NameConference on Graphics, Patterns and Images, 34 (SIBGRAPI)
Conference LocationGramado (Virtual), Brazil
DateOctober 18th to October 22nd, 2021
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeUndergraduate Work
History (UTC)2021-09-14 11:28:19 :: -> administrator ::
2021-11-12 11:47:10 :: administrator -> :: 2021
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Content TypeExternal Contribution
convolutional neural networks
deep learning
computer vision
AbstractAs 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. > SDLA > SIBGRAPI 2021 > Evaluating Loss Functions...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 14/09/2021 08:28 1.3 KiB 
Conditions of access and use area
data URL
zipped data URL
Target Filepaper.pdf
Allied materials area
Next Higher Units8JMKD3MGPEW34M/45PQ3RS
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
Description control area
e-Mail (login)