TY - GEN
T1 - De-rendering Stylized Texts
AU - Shimoda, Wataru
AU - Haraguchi, Daichi
AU - Uchida, Seiichi
AU - Yamaguchi, Kota
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85127173994&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127173994&partnerID=8YFLogxK
U2 - 10.1109/ICCV48922.2021.00111
DO - 10.1109/ICCV48922.2021.00111
M3 - Conference contribution
AN - SCOPUS:85127173994
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1056
EP - 1065
BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
Y2 - 11 October 2021 through 17 October 2021
ER -