The Surprisingly Straightforward Scene Text Removal Method With Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis

TL;DR

This paper introduces a novel scene text removal method utilizing gated attention and region of interest generation, achieving superior performance and efficiency without additional refinement steps.

Contribution

The paper proposes a simple yet effective Gated Attention and Region-of-Interest Generation approach for scene text removal, outperforming existing methods with fewer parameters and faster processing.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Achieves higher-quality text removal results with fewer parameters.

Operates efficiently without explicit text stroke masks.

Abstract

Scene text removal (STR), a task of erasing text from natural scene images, has recently attracted attention as an important component of editing text or concealing private information such as ID, telephone, and license plate numbers. While there are a variety of different methods for STR actively being researched, it is difficult to evaluate superiority because previously proposed methods do not use the same standardized training/evaluation dataset. We use the same standardized training/testing dataset to evaluate the performance of several previous methods after standardized re-implementation. We also introduce a simple yet extremely effective Gated Attention (GA) and Region-of-Interest Generation (RoIG) methodology in this paper. GA uses attention to focus on the text stroke as well as the textures and colors of the surrounding regions to remove text from the input image much more precisely. RoIG is applied to focus on only the region with text instead of the entire image to train the model more efficiently. Experimental results on the benchmark dataset show that our method significantly outperforms existing state-of-the-art methods in almost all metrics with remarkably higher-quality results. Furthermore, because our model does not generate a text stroke mask explicitly, there is no need for additional refinement steps or sub-models, making our model extremely fast with fewer parameters. The dataset and code are available at this https://github.com/naver/garnet.