MG-Gen: Single Image to Motion Graphics Generation

Takahiro Shirakawa, Tomoyuki Suzuki, Takuto Narumoto, Daichi Haraguchi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 3504-3513

Abstract

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.

Related Material

[pdf]
[bibtex]
@InProceedings{Shirakawa_2025_ICCV, author = {Shirakawa, Takahiro and Suzuki, Tomoyuki and Narumoto, Takuto and Haraguchi, Daichi}, title = {MG-Gen: Single Image to Motion Graphics Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3504-3513} }