paper-with-me

Papers

Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models

2023-11-28 · Ling Fu, Zijie Wu, Yingying Zhu, Yuliang Liu, Xiang Bai

Scene text detection techniques have garnered significant attention due to their wide-ranging applications. However, existing methods have a high demand for training data, and obtaining accurate human annotations is labor-intensive and time-consuming. As a solution, researchers have widely adopted synthetic text images as a complementary resource to real text images during pre-training. Yet there is still room for synthetic datasets to enhance the performance of scene text detectors. We contend that one main limitation of existing generation methods is the insufficient integration of foreground text with the background. To alleviate this problem, we present the Diffusion Model based Text Generator (DiffText), a pipeline that utilizes the diffusion model to seamlessly blend foreground text regions with the background's intrinsic features. Additionally, we propose two strategies to generate visually coherent text with fewer spelling errors. With fewer text instances, our produced text images consistently surpass other synthetic data in aiding text detectors. Extensive experiments on detecting horizontal, rotated, curved, and line-level texts demonstrate the effectiveness of DiffText in producing realistic text images.

📄 PDF Abstract BibTeX arXiv:2311.16555

Code (1)

99franklin/difftext 공식 구현 jax

Tasks

Image GenerationScene Text DetectionText Detection

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Vision-Language Pre-Training for Boosting Scene Text Detectors

2022-04-29 · CVPR 2022 1 · Sibo Song, Jianqiang Wan, Zhibo Yang, Jun Tang 외

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that in…

Contrastive LearningLanguage ModelingLanguage ModellingMasked Language Modeling+3

UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World

2020-03-24 · CVPR 2020 6 · Shangbang Long, Cong Yao

Synthetic data has been a critical tool for training scene text detection and recognition models. On the one hand, synthetic word images have proven to be a successful substitute for real images in training scene text re…

Image GenerationScene Text DetectionScene Text RecognitionText Detection

TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields

2024-01-01 · CVPR 2024 1 · Jialei Cui, Jianwei Du, Wenzhuo LIU, Zhouhui Lian

Acquiring large-scale well-annotated datasets is essential for training robust scene text detectors yet the process is often resource-intensive and time-consuming. While some efforts have been made to explore the syn…

Image GenerationNeRFText Detection

Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs

2025-07-21 · Apoorva Gulati, Rajesh Kumar, Vinti Agarwal, Aditya Sharma arxiv

Large Language Models (LLMs) have made it easier to create realistic fake profiles on platforms like LinkedIn. This poses a significant risk for text-based fake profile detectors. In this study, we evaluate the robustnes…

MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection

2025-04-09 · CVPR 2025 1 · Rishubh Parihar, Srinjay Sarkar, Sarthak Vora, Jogendra Kundu 외

Current monocular 3D detectors are held back by the limited diversity and scale of real-world datasets. While data augmentation certainly helps, it's particularly difficult to generate realistic scene-aware augmented dat…

Data AugmentationDiversitySynthetic Data Generation