🎰TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

$$ TextSSR ~ Capability ~ Showcase. $$

📢News

[2025.06.26] - This paper has been accepted by ICCV2025 🎉!

[2025.02.13] - The benchmark and evaluation code are available!

[2024.12.05] - The training dataset and generative dataset(v1: 0.43m and v2: 3.55m) are released!

[2024.12.04] - We released the latest model and online demo, check on ModelScope.

[2024.12.03] - Our paper is available at here.

📝TODOs

• Upload the new revised version of the manuscript
• Release the expanded large-scale synthetic dataset TextSSR-F, which contains 3.55M text instances.
• Provide publicly checkpoints and gradio demo
• Release TextSSR-benchmark dataset and evaluation code
• Release processed AnyWord-lmdb dataset
• Release our scene text synthesis dataset, TextSSR-F
• Release training and inference code

💎Visualization

$$ Model ~ Architecture ~ Display. $$

$$ Data ~ Synthesis ~ Pipeline. $$

$$ Results ~ Presentation. $$

🛠Installation

Environment Settings

1. Clone the TextSSR Repository:

   git clone https://github.com/YesianRohn/TextSSR.git
   cd TextSSR
   

2. Create a New Environment for TextSSR:

   conda create -n textssr python=3.10
   conda activate textssr
   

3. Install Required Dependencies:

   • Install PyTorch, TorchVision, Torchaudio, and the necessary CUDA version:

   conda install pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=11.8 -c pytorch -c nvidia
   

   • Install the rest of the dependencies listed in the requirements.txt file:

   pip install -r requirements.txt
   

   • Install our modified diffusers:

   cd diffusers
   pip install -e .
   cd ..
   

---

Checkpoints/Data Preparation

1. Data Preparation:

   • You can use the Anyword-3M dataset provided by Anytext. However, you will need to modify the data loading code to use AnyWordDataset instead of AnyWordLmdbDataset.
   • If you have obtained our AnyWord-lmdb dataset, simply place it in the TextSSR folder.

2. Font File Preparation:

   • You can either download the Alibaba PuHuiTi font from here, which should be named AlibabaPuHuiTi-3-85-Bold.ttf, or you can use your own custom font file.
   • Place your font file in the TextSSR folder.

3. Model Preparation:

• If you want to train the model from scratch, first download the SD2-1 model from Hugging Face.
  • Place the downloaded model in the model folder.
  • During the training process, you will obtain several model checkpoints. These should be placed sequentially in the model folder as follows:
    • vae_ft (trained VAE model)
    • step1 (trained CDM after step 1)
    • step2 (trained CDM after step 2)

After the preparations outlined above, you will have the following file structure:

TextSSR/
├── model/
│   ├── stable-diffusion-v2-1
│   ├── vae_ft
│       ├── checkpoint-x/
│       	├── vae/
│       	└── ...
│   ├── step1
│       ├── checkpoint-x/
│       	├── unet/
│       	└── ...
│   ├── step2
│       ├── checkpoint-x/
│       	├── unet/
│       	└── ...
│   └── AnyWord-lmdb/                      
│       ├── step1_lmdb/
│       ├── step2-lmdb/
├── AlibabaPuHuiTi-3-85-Bold.ttf
├── ...(the same as the GitHub code)

🚂 Training

1. Step 1: Fine-tune the VAE:

   accelerate launch --num_processes 8 train_vae.py --config configs/train_vae_cfg.py
   

2. Step 2: First stage of CDM training:

   accelerate launch --num_processes 8 train_diff.py --config configs/train_diff_step1_cfg.py
   

3. Step 3: Second stage of CDM training:

   accelerate launch --num_processes 8 train_diff.py --config configs/train_diff_step2_cfg.py
   

🔍 Inference

• Ensure the benchmark path is correctly set in infer.py.
• Run the inference process with:

  python infer.py
  

This will start the inference and generate the results.

📊Evaluation

See here.

🔗Citation

@InProceedings{Ye_2025_ICCV,
    author    = {Ye, Xingsong and Du, Yongkun and Tao, Yunbo and Chen, Zhineng},
    title     = {TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2025},
    pages     = {17464-17473}
}

🌟 Acknowledgements

Many thanks to these great projects for their contributions, which have influenced and supported our work in various ways: SynthText, TextOCR, DiffUTE, Textdiffuser & Textdiffuser-2, AnyText, UDiffText, SceneVTG, and SVTRv2.

Special thanks also go to the training frameworks: STR-Fewer-Labels and OpenOCR.