arXiv:2504.02361cs.GRcs.CV2025-04ICCV

输入一张图,自动生成可动的网页级动画图形。

MG-Gen: Single Image to Motion Graphics Generation

  • 将图像分解为可独立动画的层,用HTML和脚本控制
  • 生成动画视频,文字清晰且忠于原图
  • 适合设计师快速制作动态网页内容

我们提出MG-Gen,一种直接从单张位图生成动态图形的框架。MG-Gen将输入图像分解为由HTML表示的分层结构,为每层生成动画脚本,并最终渲染为视频。实验表明,MG-Gen在保持文字可读性和输入图像保真度方面表现优异,而当前最先进的图像到视频生成方法在此方面存在困难。代码已开源:https://github.com/CyberAgentAILab/MG-GEN。

原文摘要 · Abstract (English)

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.

图像生成动画网页

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。