Autoregressive Label-Conditioned Autoencoder for Controllable Image-To-Video Generation
Ładowanie...
Data
2023
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
Generating 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.
Opis
Słowa kluczowe
video generation, image-to-video, autoencoder, supervised PCA, generacja wideo, przetwarzanie obrazu na wideo, autoenkoder, nadzorowana PCA
Cytowanie
Kubicki 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.