Related papers: Recognition-Synergistic Scene Text Editing

With the development of deep neural networks, the demand for a significant amount of annotated training data becomes the performance bottlenecks in many fields of research and applications. Image synthesis can generate annotated images…

Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors…

Text recognition is an inherent integration of vision and language, encompassing the visual texture in stroke patterns and the semantic context among the character sequences. Towards advanced text recognition, there are three key…

Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including perspective distortions, line curvature or other style…

Scene change detection (SCD) is crucial for urban monitoring and navigation but remains challenging in real-world environments due to lighting variations, seasonal shifts, viewpoint differences, and complex urban layouts. Existing methods…

An unconstrained end-to-end text localization and recognition method is presented. The method detects initial text hypothesis in a single pass by an efficient region-based method and subsequently refines the text hypothesis using a more…

Scene text recognition has made significant progress in recent years and has become an important part of the work-flow. The widespread use of mobile devices opens up wide possibilities for using OCR technologies in everyday life. However,…

The challenging field of scene text detection requires complex data annotation, which is time-consuming and expensive. Techniques, such as weak supervision, can reduce the amount of data needed. In this paper we propose a weak supervision…

Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text. Most of existing approaches attempt to solve the problem in two or multiple stages, which is…

Recently, scene text recognition (STR) models have shown significant performance improvements. However, existing models still encounter difficulties in recognizing challenging texts that involve factors such as severely distorted and…

Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the hardest problems in this task is how to represent text instances of arbitrary shapes. Although many methods…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a…

Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected to the text…

For successful scene text recognition (STR) models, synthetic text image generators have alleviated the lack of annotated text images from the real world. Specifically, they generate multiple text images with diverse backgrounds, font…

We present a novel, training-free approach to scene change detection. Our method leverages tracking models, which inherently perform change detection between consecutive frames of video by identifying common objects and detecting new or…

Text recognition in natural scene is a challenging problem due to the many factors affecting text appearance. In this paper, we presents a method that directly transcribes scene text images to text without needing of sophisticated character…

Scene text detection task has attracted considerable attention in computer vision because of its wide application. In recent years, many researchers have introduced methods of semantic segmentation into the task of scene text detection, and…

Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text…

Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…