SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.01137 · 2024

TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

Zhineng Chen, Yongkun Du, Yunbo Tao, Xingsong Ye

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Scene text recognition (STR) suffers from challenges of either less realistic synthetic training data or the difficulty of collecting sufficient high-quality real-world data, limiting the effectiveness of trained models. Meanwhile, despite producing holistically appealing text images, diffusion-based visual text generation methods struggle to synthesize accurate and realistic instance-level text at scale. To tackle this, we introduce TextSSR: a novel pipeline for Synthesizing Scene Text Recognition training data. TextSSR targets three key synthesizing characteristics: accuracy, realism, and scalability. It achieves accuracy through a proposed region-centric text generation with position-glyph enhancement, ensuring proper character placement. It maintains realism by guiding style and appearance generation using contextual hints from surrounding text or background. This character-aware diffusion architecture enjoys precise character-level control and semantic coherence preservation, without relying on natural language prompts. Therefore, TextSSR supports large-scale generation through combinatorial text permutations. Based on these, we present TextSSR-F, a dataset of 3.55 million quality-screened text instances. Extensive experiments show that STR models trained on TextSSR-F outperform those trained on existing synthetic datasets by clear margins on common benchmarks, and further improvements are observed when mixed with real-world training data. Code is available at https://github.com/YesianRohn/TextSSR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2412.01137")
get_code_for_paper("2412.01137")
have("2412.01137")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2412.01137.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2412.01137.svg)](https://syntology.ai/paper/2412.01137)

Connect an agent — have() is free.