Autoregressive Label-Conditioned Autoencoder for Controllable Image-To-Video Generation

dc.contributor.authorKubicki, Kacper
dc.contributor.authorŚlot, Krzysztof
dc.date.accessioned2023-09-22T12:33:59Z
dc.date.available2023-09-22T12:33:59Z
dc.date.issued2023
dc.description.abstractGenerating videos from a single image with user-controlled attributes is a complex challenge in the field of computer vision, despite the significant advancements recently made in the field. This paper presents a novel approach to tackle this issue, leveraging a convolutional autoencoder with supervised principal component analysis and autoregressive inference step. The efficacy of the proposed method is evaluated on two datasets – MNIST handwritten-digits and time-lapse photos of the sky. Results from both quantitative and qualitative analyses show that the proposed approach produces high-quality videos of variable duration with user-defined attributes, while preserving the integrity of original image contents.en_EN
dc.identifier.citationKubicki K., Ślot K., Autoregressive Label-Conditioned Autoencoder for Controllable Image-To-Video Generation. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 307-311, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.49.
dc.identifier.doi10.34658/9788366741928.49
dc.identifier.isbn978-83-66741-92-8
dc.identifier.urihttp://hdl.handle.net/11652/4825
dc.identifier.urihttps://doi.org/10.34658/9788366741928.49
dc.language.isoenen_EN
dc.page.numbers. 307-311
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofWojciechowski A. (Ed.), Lipiński P. (Ed.)., Progress in Polish Artificial Intelligence Research 4, Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rightsFair use conditionen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.rights.licenseLUT Licenseen_EN
dc.subjectvideo generationen_EN
dc.subjectimage-to-videoen_EN
dc.subjectautoencoderen_EN
dc.subjectsupervised PCAen_EN
dc.subjectgeneracja wideopl_PL
dc.subjectprzetwarzanie obrazu na wideopl_PL
dc.subjectautoenkoderpl_PL
dc.subjectnadzorowana PCApl_PL
dc.titleAutoregressive Label-Conditioned Autoencoder for Controllable Image-To-Video Generationen_EN
dc.typeRozdział - monografiapl_PL
dc.typeChapter - monographen_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
49. Autoregressive_label_conditioned_Kubicki_Slot_2023.pdf
Rozmiar:
1.46 MB
Format:
Adobe Portable Document Format
Opis:
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis: