mlsanityData to 7 Oct 2026

Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realisation

arXiv 2310.00546 ↗First posted 1 Oct 2023cs.CVcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Seal-related tasks in document processing-such as seal segmentation, authenticity verification, seal removal, and text recognition under seals-hold substantial commercial importance. However, progress in these areas has been hindered by the scarcity of labeled document seal datasets, which are essential for supervised learning. To address this limitation, we propose Seal2Real, a novel generative framework designed to synthesize large-scale labeled document seal data. As part of this work, we also present Seal-DB, a comprehensive dataset containing 20,000 labeled images to support seal-related research. Seal2Real introduces a prompt prior learning architecture built upon a pre-trained Stable Diffusion model, effectively transferring its generative capability to the unsupervised domain of seal image synthesis. By producing highly realistic synthetic seal images, Seal2Real significantly enhances the performance of downstream seal-related tasks on real-world data. Experimental evaluations on the Seal-DB dataset demonstrate the effectiveness and practical value of the proposed framework. The dataset is available at https://github.com/liuyifan6613/DocBank-Document-Enhancement-Dataset.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 24 of its 48 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

24 of 48 references.

References · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  9. 2021GAN Inversion: A Surveycited by 366
  10. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulationscited by 243
  11. 2023Guiding Instruction-based Image Editing via Multimodal Large Language Modelscited by 182
  12. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Modelscited by 172
12 more
  1. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  2. 2022CLIP-Event: Connecting Text and Images with Event Structurescited by 86
  3. 2022SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognitioncited by 70
  4. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55
  5. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 46
  6. 2023DocDiff: Document Enhancement via Residual Diffusion Modelscited by 37
  7. 2023KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editingcited by 21
  8. 2023FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image Editingcited by 11
  9. 2018Improving Document Binarization via Adversarial Noise-Texture Augmentationcited by 9
  10. 2021A Survey on Deep learning based Document Image Enhancementcited by 7
  11. 2023Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancementcited by 5
  12. 2021Personalizing image enhancement for critical visual tasks: improved legibility of papyri using color processing and visual illusionscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editingcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Generative Models Actually Forge Realistic Identity Documents?
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models
  3. 2026Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
  4. 2025Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
  5. 2026TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
  6. 2024Simplified and Generalized Masked Diffusion for Discrete Data
  7. 2024Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
  8. 2024Simple and Effective Masked Diffusion Language Models