De-rendering Stylized Texts
This addresses the challenge of editing stylized text in media like posters or web pages, offering a more efficient solution than raster-based methods.
The paper tackles the problem of editing raster text in display media by proposing a text vectorization model that parses rendering parameters for reconstruction and editing, achieving artifact-free text editing compared to raster baselines.
Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instead of applying image transformation or generation in the raster domain, we learn a text vectorization model to parse all the rendering parameters including text, location, size, font, style, effects, and hidden background, then utilize those parameters for reconstruction and any editing task. Our text vectorization takes advantage of differentiable text rendering to accurately reproduce the input raster text in a resolution-free parametric format. We show in the experiments that our approach can successfully parse text, styling, and background information in the unified model, and produces artifact-free text editing compared to a raster baseline.