FETNet: Feature Erasing and Transferring Network for Scene Text Removal

by   Guangtao Lyu, et al.

The scene text removal (STR) task aims to remove text regions and recover the background smoothly in images for private information protection. Most existing STR methods adopt encoder-decoder-based CNNs, with direct copies of the features in the skip connections. However, the encoded features contain both text texture and structure information. The insufficient utilization of text features hampers the performance of background reconstruction in text removal regions. To tackle these problems, we propose a novel Feature Erasing and Transferring (FET) mechanism to reconfigure the encoded features for STR in this paper. In FET, a Feature Erasing Module (FEM) is designed to erase text features. An attention module is responsible for generating the feature similarity guidance. The Feature Transferring Module (FTM) is introduced to transfer the corresponding features in different layers based on the attention guidance. With this mechanism, a one-stage, end-to-end trainable network called FETNet is constructed for scene text removal. In addition, to facilitate research on both scene text removal and segmentation tasks, we introduce a novel dataset, Flickr-ST, with multi-category annotations. A sufficient number of experiments and ablation studies are conducted on the public datasets and Flickr-ST. Our proposed method achieves state-of-the-art performance using most metrics, with remarkably higher quality scene text removal results. The source code of our work is available at: \href{https://github.com/GuangtaoLyu/FETNet}{https://github.com/GuangtaoLyu/FETNet.


page 18

page 21

page 25

page 26

page 29

page 30


PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network

Scene text removal (STR) is a challenging task due to the complex text f...

Selective Scene Text Removal

Scene text removal (STR) is the image transformation task to remove text...

ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining

Scene text removal (STR) aims at replacing text strokes in natural scene...

Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach

Text segmentation is a prerequisite in many real-world text-related task...

Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context

Text removal has attracted increasingly attention due to its various app...

TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

Text irregularities pose significant challenges to scene text recognizer...

Please sign up or login with your details

Forgot password? Click here to reset