MG-Gen: Single Image to Motion Graphics Generation
This addresses the need for automated motion graphics creation for designers and content creators, though it appears incremental as it builds on existing decomposition and animation techniques.
The paper tackles the problem of generating motion graphics from a single raster image by decomposing it into layered HTML structures and animating them, resulting in dynamic outputs that preserve text readability and fidelity better than state-of-the-art image-to-video methods.
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.