StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Choi, Jongwoo, Seo, Kwanggyoon, Ashtari, Amirsaman, Noh, Junyong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914722863906816
author Choi, Jongwoo
Seo, Kwanggyoon
Ashtari, Amirsaman
Noh, Junyong
author_facet Choi, Jongwoo
Seo, Kwanggyoon
Ashtari, Amirsaman
Noh, Junyong
contents We propose a method that can generate cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN. Inspired by the success of recent unconditional video generation, we leverage a powerful pre-trained image generator to synthesize high-quality cinemagraphs. Unlike previous approaches that mainly utilize the latent space of a pre-trained StyleGAN, our approach utilizes its deep feature space for both GAN inversion and cinemagraph generation. Specifically, we propose multi-scale deep feature warping (MSDFW), which warps the intermediate features of a pre-trained StyleGAN at different resolutions. By using MSDFW, the generated cinemagraphs are of high resolution and exhibit plausible looping animation. We demonstrate the superiority of our method through user studies and quantitative comparisons with state-of-the-art cinemagraph generation methods and a video generation method that uses a pre-trained StyleGAN.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14186
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN
Choi, Jongwoo
Seo, Kwanggyoon
Ashtari, Amirsaman
Noh, Junyong
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
We propose a method that can generate cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN. Inspired by the success of recent unconditional video generation, we leverage a powerful pre-trained image generator to synthesize high-quality cinemagraphs. Unlike previous approaches that mainly utilize the latent space of a pre-trained StyleGAN, our approach utilizes its deep feature space for both GAN inversion and cinemagraph generation. Specifically, we propose multi-scale deep feature warping (MSDFW), which warps the intermediate features of a pre-trained StyleGAN at different resolutions. By using MSDFW, the generated cinemagraphs are of high resolution and exhibit plausible looping animation. We demonstrate the superiority of our method through user studies and quantitative comparisons with state-of-the-art cinemagraph generation methods and a video generation method that uses a pre-trained StyleGAN.
title StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2403.14186