Corpus ID: 236318544

RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image

  title={RewriteNet: Realistic Scene Text Image Generation via Editing Text in Real-world Image},
  author={Junyeop Lee and Yoonsik Kim and Seonghyeon Kim and Moonbin Yim and Seung Shin and Gayoung Lee and Sungrae Park},
Scene text editing (STE), which converts a text in a scene image into the desired text while preserving an original style, is a challenging task due to a complex intervention between text and style. To address this challenge, we propose a novel representational learning-based STE model, referred to as RewriteNet that employs textual information as well as visual information. We assume that the scene text image can be decomposed into content and style features where the former represents the… Expand

Figures and Tables from this paper


Editing Text in the Wild
This work proposes an end-to-end trainable style retention network (SRNet) that consists of three modules: text conversion module, background inpainting module and fusion module, which is the first attempt to edit text in natural images at the word level. Expand
STEFANN: Scene Text Editor Using Font Adaptive Neural Network
This paper proposes a method to modify text in an image at character-level using two different neural network architectures - FANnet to achieve structural consistency with source font and Colornet to preserve source color. Expand
SwapText: Image Based Texts Transfer in Scenes
Swapping text in scene images while preserving original fonts, colors, sizes and background textures is a challenging task due to the complex interplay between different factors, so a three-stage framework to transfer texts across scene images is presented. Expand
Scene Text Eraser
A scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model demonstrates a drastically decrease on the precision, recall and f-score compared with direct text detection way. Expand
Robust Scene Text Recognition with Automatic Rectification
RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text, which is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems. Expand
MTRNet: A Generic Scene Text Eraser
MTRNet is a conditional adversarial generative network (cGAN) with an auxiliary mask that makes the cGAN a generic text eraser, but also enables stable training and early convergence on a challenging large-scale synthetic dataset, initially proposed for text detection in real scenes. Expand
Recognizing Text with Perspective Distortion in Natural Scenes
This paper introduces a new dataset called StreetViewText-Perspective, which contains texts in street images with a great variety of viewpoints and significantly outperforms the state-of-the-art on perspective texts of arbitrary orientations. Expand
Towards Accurate Scene Text Recognition With Semantic Reasoning Networks
This work proposes a novel end-to-end trainable framework named semantic reasoning network (SRN) for accurate scene text recognition, where a global semantic reasoning module (GSRM) is introduced to capture global semantic context through multi-way parallel transmission. Expand
Character Region Awareness for Text Detection
A new scene text detection method to effectively detect text area by exploring each character and affinity between characters by exploiting both the given character- level annotations for synthetic images and the estimated character-level ground-truths for real images acquired by the learned interim model. Expand
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
The COCO-Text dataset is described, which contains over 173k text annotations in over 63k images and presents an analysis of three leading state-of-the-art photo Optical Character Recognition (OCR) approaches on the dataset. Expand