Salvato in:
Dettagli Bibliografici
Autori principali: Shirakawa, Takahiro, Suzuki, Tomoyuki, Narumoto, Takuto, Haraguchi, Daichi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.02361
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913939551420416
author Shirakawa, Takahiro
Suzuki, Tomoyuki
Narumoto, Takuto
Haraguchi, Daichi
author_facet Shirakawa, Takahiro
Suzuki, Tomoyuki
Narumoto, Takuto
Haraguchi, Daichi
contents We introduce MG-Gen, a framework that generates motion graphics directly from a single raster image. MG-Gen decompose a single raster image into layered structures represented as HTML, generate animation scripts for each layer, and then render them into a video. Experiments confirm MG-Gen generates dynamic motion graphics while preserving text readability and fidelity to the input conditions, whereas state-of-the-art image-to-video generation methods struggle with them. The code is available at https://github.com/CyberAgentAILab/MG-GEN.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MG-Gen: Single Image to Motion Graphics Generation
Shirakawa, Takahiro
Suzuki, Tomoyuki
Narumoto, Takuto
Haraguchi, Daichi
Graphics
Computer Vision and Pattern Recognition
We introduce MG-Gen, a framework that generates motion graphics directly from a single raster image. MG-Gen decompose a single raster image into layered structures represented as HTML, generate animation scripts for each layer, and then render them into a video. Experiments confirm MG-Gen generates dynamic motion graphics while preserving text readability and fidelity to the input conditions, whereas state-of-the-art image-to-video generation methods struggle with them. The code is available at https://github.com/CyberAgentAILab/MG-GEN.
title MG-Gen: Single Image to Motion Graphics Generation
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.02361