Sorry, you need to enable JavaScript to visit this website.

Two-Stage Seamless Text Erasing On Real-World Scene Images

Citation Author(s):
Benjamin Conrad, Pei-i Chen
Submitted by:
Benjamin Conrad
Last updated:
24 September 2021 - 11:01am
Document Type:
Poster
Document Year:
2021
Event:

Abstract 

Abstract: 

Erasing text from images is a common image-editing task in film industry and shared media. Existing text-erasing models either tend to produce artifacts or fail to remove all the text in real-world images. In this paper, we follow a two-stage text erasing framework that first masks the text by segmentation, and then inpaints the masked region to create a text-erased image. Our proposed text mask generator is designed to accurately cover text, which combined with inpainting, can produce reliable text-erased results. In the inpainting model, we propose a Multiscale Gradient Reconstruction Loss to generate sharp realistic-looking images. Our model achieves state-of-the-art results on both synthetic and real world data in both quantitative and qualitative measures.

up
0 users have voted:

Dataset Files

two_stage_text_erasing_poster.pdf

(13)

two_stage_text_erasing_slides.pdf

(18)