De-rendering Stylized Texts

TL;DR

This paper introduces a text vectorization method for editing rasterized stylized texts by parsing rendering parameters, enabling high-quality, artifact-free modifications in display media.

Contribution

It presents a novel text vectorization approach that accurately extracts rendering parameters for raster text editing, improving over raster-based methods.

Findings

Successful parsing of text, style, and background information.

Artifact-free text editing results.

Outperforms raster baselines in quality.

Abstract

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.