Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Interactive landscape–scale cloud animation using DCGAN
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science. (DIDA)ORCID iD: 0000-0002-6920-9983
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science. (DIDA)ORCID iD: 0000-0002-4390-411X
Blekinge Institute of Technology. student.
Blekinge Institute of Technology. student.
2023 (English)In: Frontiers in Computer Science, E-ISSN 2624-9898, Vol. 5, article id 957920Article in journal (Refereed) Published
Abstract [en]

This article presents an interactive method for 3D cloud animation at the landscape scale by employing machine learning. To this end, we utilize deep convolutional generative adversarial network (DCGAN) on GPU for training on home-captured cloud videos and producing coherent animation frames. We limit the size of input images provided to DCGAN, thereby reducing the training time and yet producing detailed 3D animation frames. This is made possible through our preprocessing of the source videos, wherein several corrections are applied to the extracted frames to provide an adequate input training data set to DCGAN. A significant advantage of the presented cloud animation is that it does not require any underlying physics simulation. We present detailed results of our approach and verify its effectiveness using human perceptual evaluation. Our results indicate that the proposed method is capable of convincingly realistic 3D cloud animation, as perceived by the participants, without introducing too much computational overhead.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2023. Vol. 5, article id 957920
Keywords [en]
cloud animation, deep convolutional generative adversarial networks (DCGAN), multimedia (image/video/music), machine learning, image processing
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:bth-24355DOI: 10.3389/fcomp.2023.957920ISI: 000954548500001Scopus ID: 2-s2.0-85150491207OAI: oai:DiVA.org:bth-24355DiVA, id: diva2:1741993
Available from: 2023-03-08 Created: 2023-03-08 Last updated: 2023-12-28Bibliographically approved

Open Access in DiVA

fulltext(2310 kB)223 downloads
File information
File name FULLTEXT01.pdfFile size 2310 kBChecksum SHA-512
b7794d646061e5e3b6926a3540892d58103150b67ce963e7092338f7e5a0b774675d92c0fae64ea6f8607cc729ba8b39a919606cc3d809b5bbc58aa17bddd1f2
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopushttps://www.frontiersin.org/articles/10.3389/fcomp.2023.957920

Authority records

Goswami, PrashantCheddad, Abbas

Search in DiVA

By author/editor
Goswami, PrashantCheddad, Abbas
By organisation
Department of Computer ScienceBlekinge Institute of Technology
In the same journal
Frontiers in Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 223 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 386 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf